Тип	Название	Значение
stylesheet		/luky.min.css
js		https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js
js		http://127.0.0.1:8787/userscripts/research-overlay-inline.js
js		http://127.0.0.1:8787/userscripts/mh-helper-rail.js
js		/js/main.js

Исправить

Серверные заголовки

Кол-во: 19

HTTP-заголовки ответа сервера ?

Найдены серверные заголовки 19шт. Подробнее про серверные заголовки.

Показать полный список серверных заголовков

Ключ	Значение
Server	GitHub.com
x-origin-cache	HIT
Access-Control-Allow-Origin	*
Strict-Transport-Security	max-age=31556952
ETag	"6a8a3c9c-7cd7a"
Cache-Control	max-age=600
x-proxy-cache	MISS
x-github-request-id	79BE:0A4F:E2D31:F7ACE:6A8B0483
x-github-edge-region	swedencentral
Accept-Ranges	bytes
Age	0
Date	Sun, 23 Aug 2026 14:32:36 GMT
Via	1.1 varnish
X-Served-By	cache-bma-essb1270029-BMA
X-Cache	MISS
x-cache-hits	0
x-timer	S1787495556.257076,VS0,VE168
Vary	Accept-Encoding
x-fastly-request-id	91a39fc480b89917d4b1411684ed226c0fe50688

CMS

Не определена

Система управления сайтом (движок) ?

CMS не определена. Вероятно, сайт самописный либо движок надёжно скрыт. Это не ошибка.

Веб-сервер

GitHub.com

Программное обеспечение сервера ?

В заголовке Server указано: GitHub.com.

Мета-теги Готовность: 80%

Title

Michal Valko - Publications

Заголовок страницы в браузере и поисковой выдаче ?

Необходимо увеличить число символов в title (текущее значение: 27, оптимально: от 40 до 45)

Дублей словоформ в title не найдено.

Исправить

Description

Publications by Michal Valko - research on reinforcement learning, bandits, LLM alignment at NeurIPS, ICML, ICLR, and COLT.

Описание страницы в поисковой выдаче (сниппет) ?

Число символов в description 123 оптимально (норма: от 120 до 130).

Keywords

Michal Valko, publications, reinforcement learning, bandits, LLM alignment, RLHF, NeurIPS, ICML, ICLR, COLT, AISTATS, machine learning research

Список ключевых слов страницы (устаревший тег) ?

Keywords установлены.

Канонический Url

https://misovalko.github.io/research.html

Указывает поисковику основную версию страницы ?

Канонический Url прописан корректно.

Robots

Ошибок нет

Директивы для поисковых роботов на уровне страницы ?

Meta-тег robots не указан. Страница свободна для индексации.

Адаптивность

width=device-width, initial-scale=1.0

Настройка масштабирования на мобильных устройствах ?

Meta-тег viewport со значением-константой width=device-width задаёт ширину страницы в соответствии с размером экрана.

Meta-тег viewport со значением initial-scale=1.0 определяет масштаб 1:1, т.е. «не масштабировать».

Разметка OpenGraph

Кол-во: 10

Мета-теги для красивых превью в соцсетях ?

Разметка OpenGraph задана. Страница оптимизирована под социальные сети.

Показать полный список og мета-тегов

Тип	Значение
og:title	Michal Valko - Publications
og:description	Publications on reinforcement learning, bandits, LLM alignment, and self-supervised learning at NeurIPS, ICML, ICLR, COLT, and AISTATS.
og:image	https://misovalko.github.io/images/common/mvgr20.webp
og:image:width	1200
og:image:height	630
og:url	https://misovalko.github.io/research.html
og:type	website
og:locale	en_US
og:site_name	Michal Valko
og:image:alt	Photo of Michal Valko

Все мета-теги

Кол-во: 1693

Полный список мета-тегов страницы ?

Найдены мета-теги 1693шт. Мета-теги не видимы для человека и предназначены для обмена информацией между веб-страницей и поисковыми системами, браузерами и другими веб-службами. С ними роботы 🤖 и устройства ведут себя более ожидаемо.

Показать полный список мета-тегов

Тип	Название	Значение
name	viewport	width=device-width, initial-scale=1.0
name	theme-color	#2c5aa0
name	referrer	strict-origin-when-cross-origin
name	author	Michal Valko
name	keywords	Michal Valko, publications, reinforcement learning, bandits, LLM alignment, RLHF, NeurIPS, ICML, ICLR, COLT, AISTATS, machine learning research
name	description	Publications by Michal Valko - research on reinforcement learning, bandits, LLM alignment at NeurIPS, ICML, ICLR, and COLT.
name	citation_title	DiG-bench: Discovery in Games
name	citation_author	Ruairidh M. Battleday
name	citation_author	Kai Sandbrink
name	citation_author	Jimi Cullen-Drohan
name	citation_author	Zihan Yan
name	citation_author	Timothy Muller
name	citation_author	Clare Maguire
name	citation_author	Ales Kubicek
name	citation_author	Fraser Greenlee-Scott
name	citation_author	Sukrit Sumant
name	citation_author	Tri Dao
name	citation_author	Jürgen Schmidhuber
name	citation_author	Michal Valko
name	citation_author	Joshua Tenenbaum
name	citation_author	Thomas L. Griffiths
name	citation_author	Zeb Kurth-Nelson
name	citation_author	James C.R. Whittington
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/battleday2026dig.pdf
name	citation_title	Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier
name	citation_author	Côme Fiegel
name	citation_author	Pierre Ménard
name	citation_author	Tadashi Kozuno
name	citation_author	Michal Valko
name	citation_author	Vianney Perchet
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/fiegel2026optimal.pdf
name	citation_arxiv_id	2604.15242
name	citation_title	RL-finetuning LLMs from on- and off-policy data with a single algorithm
name	citation_author	Yunhao Tang
name	citation_author	Taco Cohen
name	citation_author	David W. Zhang
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/tang2025rlfinetuning.pdf
name	citation_arxiv_id	2503.19612
name	citation_title	Understanding the performance gap between online and offline alignment algorithms
name	citation_author	Yunhao Tang
name	citation_author	Daniel Zhaohan Guo
name	citation_author	Zeyu Zheng
name	citation_author	Daniele Calandriello
name	citation_author	Yuan Cao
name	citation_author	Eugene Tarassov
name	citation_author	Rémi Munos
name	citation_author	Bernardo Ávila Pires
name	citation_author	Michal Valko
name	citation_author	Yong Cheng
name	citation_author	Will Dabney
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/tang2025understanding.pdf
name	citation_arxiv_id	2405.08448
name	citation_title	Learning to act greedily: Polymatroid semi-bandits
name	citation_author	Branislav Kveton
name	citation_author	Zheng Wen
name	citation_author	Azin Ashkan
name	citation_author	Michal Valko
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/kveton2016learning.pdf
name	citation_journal_title	Journal of Machine Learning Research
name	citation_arxiv_id	1405.7752
name	citation_title	Optimal design for reward modeling in RLHF
name	citation_author	Antoine Scheid
name	citation_author	Étienne Boursier
name	citation_author	Alain Durmus
name	citation_author	Michael I Jordan
name	citation_author	Pierre Ménard
name	citation_author	Éric Moulines
name	citation_author	Michal Valko
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/scheid2024optimal.arxiv.pdf
name	citation_arxiv_id	2410.17055
name	citation_title	A new bound on the cumulant generating function of Dirichlet processes
name	citation_author	Pierre Perrault
name	citation_author	Denis Belomestny
name	citation_author	Pierre Ménard
name	citation_author	Éric Moulines
name	citation_author	Alexey Naumov
name	citation_author	Daniil Tiapkin
name	citation_author	Michal Valko
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/perrault2025cumulant.pdf
name	citation_arxiv_id	2409.18621
name	citation_title	Sharp deviations bounds for Dirichlet weighted sums with application to analysis of Bayesian algorithms
name	citation_author	Denis Belomestny
name	citation_author	Pierre Ménard
name	citation_author	Alexey Naumov
name	citation_author	Daniil Tiapkin
name	citation_author	Michal Valko
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/belomestny2025sharp.pdf
name	citation_arxiv_id	2304.03056
name	citation_title	KL-entropy-regularized RL with a generative model is minimax optimal
name	citation_author	Tadashi Kozuno
name	citation_author	Wenhao Yang
name	citation_author	Nino Vieillard
name	citation_author	Toshinori Kitamura
name	citation_author	Yunhao Tang
name	citation_author	Jincheng Mei
name	citation_author	Pierre Ménard
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_author	Olivier Pietquin
name	citation_author	Matthieu Geist
name	citation_author	Csaba Szepesvári
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/kozuno2025kl.pdf
name	citation_arxiv_id	2205.14211
name	citation_title	On the approximation relationship between optimizing ratio of submodular (RS) and difference of submodular (DS) functions
name	citation_author	Pierre Perrault
name	citation_author	Jennifer Healey
name	citation_author	Zheng Wen
name	citation_author	Michal Valko
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/perrault2025submodular.pdf
name	citation_arxiv_id	2101.01631
name	citation_title	Language generation with replay: A learning-theoretic view of model collapse
name	citation_author	Giorgio Racca
name	citation_author	Michal Valko
name	citation_author	Amartya Sanyal
name	citation_publication_date	2026
name	citation_pdf_url	https://misovalko.github.io/publications/racca2025language.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2603.11784
name	citation_title	The harder path: Last iterate convergence for uncoupled learning in zero-sum games with bandit feedback
name	citation_author	Côme Fiegel
name	citation_author	Pierre Ménard
name	citation_author	Tadashi Kozuno
name	citation_author	Michal Valko
name	citation_author	Vianney Perchet
name	citation_publication_date	2025
name	citation_pdf_url	https://misovalko.github.io/publications/fiegel2025harder.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Proximal point Nash learning from human feedback
name	citation_author	Daniil Tiapkin
name	citation_author	Daniele Calandriello
name	citation_author	Denis Belomestny
name	citation_author	Éric Moulines
name	citation_author	Alexey Naumov
name	citation_author	Kashif Rasul
name	citation_author	Michal Valko
name	citation_author	Pierre Ménard
name	citation_publication_date	2025
name	citation_pdf_url	https://misovalko.github.io/publications/tiapkin2026accelerating.pdf
name	citation_conference_title	Conference on Learning Theory
name	citation_arxiv_id	2505.19731
name	citation_title	Generation of an output token sequence from an input token sequence using two language model neural networks
name	citation_author	Tianlin Liu
name	citation_author	Shangmin Guo
name	citation_author	Daniele Calandriello
name	citation_author	Quentin Berthet
name	citation_author	Felipe Llinares López
name	citation_author	Jessica Hoffmann
name	citation_author	Lucas Dixon
name	citation_author	Michal Valko
name	citation_author	Mathieu Blondel
name	citation_publication_date	2025
name	citation_pdf_url	https://misovalko.github.io/publications/liu2025generation.pdf
name	citation_title	Reinforcement learning using hindsight to model unpredictable aspects of the future
name	citation_author	Daniel Jarrett
name	citation_author	Corentin Tallec
name	citation_author	Florent Altché
name	citation_author	Thomas Mesnard
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2025
name	citation_pdf_url	https://patentimages.storage.googleapis.com/dc/cb/0f/ef1796e1cb36a0/US20250067291A1.pdf
name	citation_title	Preference optimization with multi-sample comparisons
name	citation_author	Chaoqi Wang
name	citation_author	Zhuokai Zhao
name	citation_author	Chen Zhu
name	citation_author	Karthik Abinav Sankararaman
name	citation_author	Michal Valko
name	citation_author	Xuefei Cao
name	citation_author	Zhaorun Chen
name	citation_author	Madian Khabsa
name	citation_author	Yuxin Chen
name	citation_author	Hao Ma
name	citation_author	Sinong Wang
name	citation_publication_date	2025
name	citation_pdf_url	https://misovalko.github.io/publications/wang2025preference.pdf
name	citation_conference_title	International Conference on Learning Representations
name	citation_arxiv_id	2410.12138
name	citation_title	The Llama 3 herd of models
name	citation_author	Llama Team: Aaron Grattafiori
name	citation_author	Abhimanyu Dubey
name	citation_author	Abhinav Jauhri
name	citation_author	Abhinav Pandey
name	citation_author	Abhishek Kadian
name	citation_author	... Michal Valko ... Zef Rosnbrick
name	citation_author	Zhaoduo Wen
name	citation_author	Zhenyu Yang
name	citation_author	Zhiwei Zhao
name	citation_author	Zhiyu Ma
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/llama2024llama3.pdf
name	citation_arxiv_id	2407.21783
name	citation_title	Metacognitive capabilities of LLMs: An exploration in mathematical problem solving
name	citation_author	Aniket Didolkar
name	citation_author	Anirudh Goyal
name	citation_author	Nan Rosemary Ke
name	citation_author	Siyuan Guo
name	citation_author	Michal Valko
name	citation_author	Timothy Lillicrap
name	citation_author	Danilo Rezende
name	citation_author	Yoshua Bengio
name	citation_author	Michael Mozer
name	citation_author	Sanjeev Arora
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/didolkar2024metacognitive.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2405.12205
name	citation_title	Local and adaptive mirror descents in extensive-form games
name	citation_author	Côme Fiegel
name	citation_author	Pierre Ménard
name	citation_author	Tadashi Kozuno
name	citation_author	Rémi Munos
name	citation_author	Vianney Perchet
name	citation_author	Michal Valko
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/fiegel2024local.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2309.00656
name	citation_title	Nash learning from human feedback
name	citation_author	Rémi Munos*
name	citation_author	Michal Valko
name	citation_author	Daniele Calandriello*
name	citation_author	Mohammad Gheshlaghi Azar*
name	citation_author	Mark Rowland*
name	citation_author	Daniel Guo*
name	citation_author	Yunhao Tang*
name	citation_author	Matthieu Geist*
name	citation_author	Thomas Mesnard
name	citation_author	Andrea Michi
name	citation_author	Marco Selvi
name	citation_author	Sertan Girgin
name	citation_author	Nikola Momchev
name	citation_author	Olivier Bachem
name	citation_author	Daniel J. Mankowitz
name	citation_author	Doina Precup
name	citation_author	Bilal Piot
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/munos2024nash.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2312.00886
name	citation_title	Human alignment of large language models through online preference optimisation
name	citation_author	Daniele Calandriello
name	citation_author	Daniel Guo
name	citation_author	Rémi Munos
name	citation_author	Mark Rowland
name	citation_author	Yunhao Tang
name	citation_author	Bernardo Ávila Pires
name	citation_author	Pierre Harvey Richemond
name	citation_author	Charline Le Lan
name	citation_author	Michal Valko
name	citation_author	Tianqi Liu
name	citation_author	Rishabh Joshi
name	citation_author	Zeyu Zheng
name	citation_author	Bilal Piot
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2024human.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2403.08635
name	citation_title	Generalized preference optimization: A unified approach to offline alignment
name	citation_author	Yunhao Tang
name	citation_author	Zhaohan Daniel Guo
name	citation_author	Zeyu Zheng
name	citation_author	Daniele Calandriello
name	citation_author	Rémi Munos
name	citation_author	Mark Rowland
name	citation_author	Pierre Harvey Richemond
name	citation_author	Michal Valko
name	citation_author	Bernardo Ávila Pires
name	citation_author	Bilal Piot
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/tang2024generalized.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2402.05749
name	citation_title	Decoding-time realignment of language models
name	citation_author	Tianlin Liu
name	citation_author	Shangmin Guo
name	citation_author	Leonardo Bianco
name	citation_author	Daniele Calandriello
name	citation_author	Quentin Berthet
name	citation_author	Felipe Llinares
name	citation_author	Jessica Hoffmann
name	citation_author	Lucas Dixon
name	citation_author	Michal Valko
name	citation_author	Mathieu Blondel
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/liu2024decodingtime.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2402.02992
name	citation_title	A general theoretical paradigm to understand learning from human preferences
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Mark Rowland
name	citation_author	Bilal Piot
name	citation_author	Zhaohan Daniel Guo
name	citation_author	Daniele Calandriello
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/azar2024unified.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	2310.12036
name	citation_title	Unlocking the power of representations in long-term novelty-based exploration
name	citation_author	Alaa Saade
name	citation_author	Steven Kapturowski
name	citation_author	Daniele Calandriello
name	citation_author	Charles Blundell
name	citation_author	Pablo Sprechmann
name	citation_author	Leopoldo Sarra
name	citation_author	Oliver Groth
name	citation_author	Michal Valko
name	citation_author	Bilal Piot
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/saade2024unlocking.pdf
name	citation_conference_title	International Conference on Learning Representations
name	citation_arxiv_id	2305.01521
name	citation_title	Demonstration-regularized RL
name	citation_author	Daniil Tiapkin
name	citation_author	Denis Belomestny
name	citation_author	Daniele Calandriello
name	citation_author	Éric Moulines
name	citation_author	Alexey Naumov
name	citation_author	Pierre Perrault
name	citation_author	Michal Valko
name	citation_author	Pierre Ménard
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/tiapkin2024demonstrationregularized.pdf
name	citation_conference_title	International Conference on Learning Representations
name	citation_arxiv_id	2310.17303
name	citation_title	rlberry: A reinforcement learning library for research and education
name	citation_author	Omar Darwiche Domingues
name	citation_author	Yannis Flet-Berliac
name	citation_author	Edouard Leurent
name	citation_author	Pierre Ménard
name	citation_author	Xuedong Shang
name	citation_author	Michal Valko
name	citation_publication_date	2024
name	citation_pdf_url	https://misovalko.github.io/publications/domingues2024rlberry.pdf
name	citation_title	Reinforcement learning by directly learning an advantage function
name	citation_author	Yunhao Tang
name	citation_author	Rémi Munos
name	citation_author	Mark Daniel Rowland
name	citation_author	Michal Valko
name	citation_publication_date	2024
name	citation_pdf_url	https://patentimages.storage.googleapis.com/7b/d9/a2/ae0b0b4e89fc49/US20240273378A1.pdf
name	citation_title	Model-free posterior sampling via learning rate randomization
name	citation_author	Daniil Tiapkin
name	citation_author	Denis Belomestny
name	citation_author	Daniele Calandriello
name	citation_author	Éric Moulines
name	citation_author	Rémi Munos
name	citation_author	Alexey Naumov
name	citation_author	Pierre Perrault
name	citation_author	Michal Valko
name	citation_author	Pierre Ménard
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/tiapkin2023model-free.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2310.18186
name	citation_title	Middle-mile logistics through the lens of goal-conditioned reinforcement learning
name	citation_author	Onno Eberhard
name	citation_author	Thibaut Cuvelier
name	citation_author	Michal Valko
name	citation_author	Bruno Adrien De Backer
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/eberhard2023middle-mile.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_title	Curiosity in hindsight: Intrinsic exploration in stochastic environments
name	citation_author	Daniel Jarrett
name	citation_author	Corentin Tallec
name	citation_author	Florent Altché
name	citation_author	Thomas Mesnard
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/jarrett2022curiosity.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2211.10515
name	citation_title	VA-learning as a more efficient alternative to Q-learning
name	citation_author	Yunhao Tang
name	citation_author	Rémi Munos
name	citation_author	Mark Rowland
name	citation_author	Michal Valko
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/tang2023valearning.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2305.18161
name	citation_title	Fast rates for maximum entropy exploration
name	citation_author	Daniil Tiapkin
name	citation_author	Denis Belomestny
name	citation_author	Daniele Calandriello
name	citation_author	Éric Moulines
name	citation_author	Rémi Munos
name	citation_author	Alexey Naumov
name	citation_author	Pierre Perrault
name	citation_author	Yunhao Tang
name	citation_author	Michal Valko
name	citation_author	Pierre Ménard
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/tiapkin2023fast.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2303.08059
name	citation_title	Adapting to game trees in zero-sum imperfect information games
name	citation_author	Côme Fiegel
name	citation_author	Pierre Ménard
name	citation_author	Tadashi Kozuno
name	citation_author	Rémi Munos
name	citation_author	Vianney Perchet
name	citation_author	Michal Valko
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/fiegel2023adapting.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2212.12567
name	citation_title	Understanding self-predictive learning for reinforcement learning
name	citation_author	Yunhao Tang
name	citation_author	Zhaohan Daniel Guo
name	citation_author	Pierre Harvey Richemond
name	citation_author	Bernardo Ávila Pires
name	citation_author	Yash Chandak
name	citation_author	Rémi Munos
name	citation_author	Mark Rowland
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Charline Le Lan
name	citation_author	Clare Lyle
name	citation_author	András György
name	citation_author	Shantanu Thakoor
name	citation_author	Will Dabney
name	citation_author	Bilal Piot
name	citation_author	Daniele Calandriello
name	citation_author	Michal Valko
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/tang2023selfpredictive.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2212.03319
name	citation_title	DoMo-AC: Doubly multi-step off-policy actor-critic algorithm
name	citation_author	Yunhao Tang
name	citation_author	Tadashi Kozuno
name	citation_author	Mark Rowland
name	citation_author	Anna Harutyunyan
name	citation_author	Rémi Munos
name	citation_author	Bernardo Ávila Pires
name	citation_author	Michal Valko
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/tang2023domoac.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2305.18501
name	citation_title	Regularization and variance-weighted regression achieves minimax optimality in linear MDPs: Theory and practice
name	citation_author	Toshinori Kitamura
name	citation_author	Tadashi Kozuno
name	citation_author	Yunhao Tang
name	citation_author	Nino Vieillard
name	citation_author	Michal Valko
name	citation_author	Wenhao Yang
name	citation_author	Jincheng Mei
name	citation_author	Pierre Ménard
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Rémi Munos
name	citation_author	Olivier Pietquin
name	citation_author	Matthieu Geist
name	citation_author	Csaba Szepesvári
name	citation_author	Wataru Kumagai
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/kitamura2023regularization.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2305.13185
name	citation_title	Quantile credit assignment
name	citation_author	Thomas Mesnard
name	citation_author	Wenqi Chen
name	citation_author	Alaa Saade
name	citation_author	Yunhao Tang
name	citation_author	Mark Rowland
name	citation_author	Theophane Weber
name	citation_author	Clare Lyle
name	citation_author	Audrunas Gruslys
name	citation_author	Michal Valko
name	citation_author	Will Dabney
name	citation_author	Georg Ostrovski
name	citation_author	Éric Moulines
name	citation_author	Rémi Munos
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/mesnard2023quantile.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Half-Hop: A graph upsampling approach for slowing down message passing
name	citation_author	Mehdi Azabou
name	citation_author	Venkataramana Ganesh
name	citation_author	Shantanu Thakoor
name	citation_author	Chi-Heng Lin
name	citation_author	Lakshmi Sathidevi
name	citation_author	Ran Liu
name	citation_author	Michal Valko
name	citation_author	Petar Veličković
name	citation_author	Eva L Dyer
name	citation_publication_date	2023
name	citation_pdf_url	https://misovalko.github.io/publications/azabou2023halfhop.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2308.09198
name	citation_title	Reinforcement learning using density estimation with online clustering for exploration
name	citation_author	Alaa Saade
name	citation_author	Steven Kapturowski
name	citation_author	Daniele Calandriello
name	citation_author	Charles Blundell
name	citation_author	Michal Valko
name	citation_author	Pablo Sprechmann
name	citation_author	Bilal Piot
name	citation_publication_date	2023
name	citation_pdf_url	https://patentimages.storage.googleapis.com/63/f7/bb/9cb89e26b1913c/WO2024057306A1.pdf
name	citation_title	BYOL-Explore: Exploration by bootstrapped prediction
name	citation_author	Zhaohan Daniel Guo
name	citation_author	Shantanu Thakoor
name	citation_author	Miruna Pîslar
name	citation_author	Bernardo Ávila Pires
name	citation_author	Florent Altché
name	citation_author	Corentin Tallec
name	citation_author	Alaa Saade
name	citation_author	Daniele Calandriello
name	citation_author	Jean-Bastien Grill
name	citation_author	Yunhao Tang
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Bilal Piot
name	citation_publication_date	2022
name	citation_pdf_url	https://misovalko.github.io/publications/guo2022byol.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2206.08332
name	citation_title	Optimistic posterior sampling for reinforcement learning with few samples and tight guarantees
name	citation_author	Daniil Tiapkin
name	citation_author	Denis Belomestny
name	citation_author	Daniele Calandriello
name	citation_author	Éric Moulines
name	citation_author	Rémi Munos
name	citation_author	Alexey Naumov
name	citation_author	Mark Rowland
name	citation_author	Michal Valko
name	citation_author	Pierre Ménard
name	citation_publication_date	2022
name	citation_pdf_url	https://misovalko.github.io/publications/tiapkin2022optimistic.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2209.14414
name	citation_title	From Dirichlet to Rubin: Optimistic exploration in RL without bonuses
name	citation_author	Daniil Tiapkin
name	citation_author	Denis Belomestny
name	citation_author	Éric Moulines
name	citation_author	Alexey Naumov
name	citation_author	Sergey Samsonov
name	citation_author	Yunhao Tang
name	citation_author	Michal Valko
name	citation_author	Pierre Ménard
name	citation_publication_date	2022
name	citation_pdf_url	https://misovalko.github.io/publications/tiapkin2022dirichlet.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2205.07704
name	citation_title	Retrieval-augmented reinforcement learning
name	citation_author	Anirudh Goyal
name	citation_author	Abram L Friesen
name	citation_author	Theophane Weber
name	citation_author	Andrea Banino
name	citation_author	Nan Rosemary Ke
name	citation_author	Adrià Puigdomènech Badia
name	citation_author	Ksenia Konyushkova
name	citation_author	Michal Valko
name	citation_author	Simon Osindero
name	citation_author	Timothy P Lillicrap
name	citation_author	Nicolas Heess
name	citation_author	Charles Blundell
name	citation_publication_date	2022
name	citation_pdf_url	https://misovalko.github.io/publications/goyal2022retrieval.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2202.08417
name	citation_title	Scaling Gaussian process optimization by evaluating a few unique candidates multiple times
name	citation_author	Daniele Calandriello
name	citation_author	Luigi Carratino
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_author	Lorenzo Rosasco
name	citation_publication_date	2022
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2022scaling.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2201.12909
name	citation_title	Large-scale representation learning on graphs via bootstrapping
name	citation_author	Shantanu Thakoor
name	citation_author	Corentin Tallec
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Mehdi Azabou
name	citation_author	Eva L. Dyer
name	citation_author	Rémi Munos
name	citation_author	Petar Veličković
name	citation_author	Michal Valko
name	citation_publication_date	2022
name	citation_pdf_url	https://misovalko.github.io/publications/thakoor2022bootstrapped.pdf
name	citation_conference_title	International Conference on Learning Representations
name	citation_arxiv_id	2102.06514
name	citation_title	Adaptive multi-goal exploration
name	citation_author	Jean Tarbouriech
name	citation_author	Omar Darwiche Domingues
name	citation_author	Pierre Ménard
name	citation_author	Matteo Pirotta
name	citation_author	Michal Valko
name	citation_author	Alessandro Lazaric
name	citation_publication_date	2022
name	citation_pdf_url	https://misovalko.github.io/publications/tarbouriech2022adaptive.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	2111.12045
name	citation_title	Marginalized operators for off-policy reinforcement learning
name	citation_author	Yunhao Tang
name	citation_author	Mark Rowland
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2022
name	citation_pdf_url	https://misovalko.github.io/publications/tang2022marginalized.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	2203.16177
name	citation_title	Drop, swap, and generate: A self-supervised approach for generating neural activity
name	citation_author	Ran Liu
name	citation_author	Mehdi Azabou
name	citation_author	Max Dabagia
name	citation_author	Chi-Heng Lin
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Keith B. Hengen
name	citation_author	Michal Valko
name	citation_author	Eva L. Dyer
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/liu2021drop.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2111.02338
name	citation_title	Stochastic shortest path: Minimax, parameter-free and towards horizon-free regret
name	citation_author	Jean Tarbouriech
name	citation_author	Runlong Zhou
name	citation_author	Simon S. Du
name	citation_author	Matteo Pirotta
name	citation_author	Michal Valko
name	citation_author	Alessandro Lazaric
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/tarbouriech2021stochastic.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2104.11186
name	citation_title	A provably efficient sample collection strategy for reinforcement learning
name	citation_author	Jean Tarbouriech
name	citation_author	Matteo Pirotta
name	citation_author	Michal Valko
name	citation_author	Alessandro Lazaric
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/tarbouriech2021provably.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2007.06437
name	citation_title	Model-free learning for two-player zero-sum partially observable Markov games with perfect recall
name	citation_author	Tadashi Kozuno*
name	citation_author	Pierre Ménard*
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/kozuno2021model-free.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2106.06279
name	citation_title	Unifying gradient estimators for meta-reinforcement learning via off-policy evaluation
name	citation_author	Yunhao Tang*
name	citation_author	Tadashi Kozuno*
name	citation_author	Mark Rowland
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/tang2021unifying.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2106.13125
name	citation_title	Broaden your views for self-supervised video learning
name	citation_author	Adrià Recasens
name	citation_author	Pauline Luc
name	citation_author	Jean-Baptiste Alayrac
name	citation_author	Luyu Wang
name	citation_author	Florian Strub
name	citation_author	Corentin Tallec
name	citation_author	Mateusz Malinowski
name	citation_author	Viorica Patraucean
name	citation_author	Florent Altché
name	citation_author	Michal Valko
name	citation_author	Jean-Bastien Grill
name	citation_author	Aäron van den Oord
name	citation_author	Andrew Zisserman
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/recasens2021broaden.pdf
name	citation_conference_title	International Conference on Computer Vision
name	citation_arxiv_id	2103.16559
name	citation_title	UCB momentum Q-learning: Correcting the bias without forgetting
name	citation_author	Pierre Ménard
name	citation_author	Omar Darwiche Domingues
name	citation_author	Xuedong Shang
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/menard2021ucb.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2103.01312
name	citation_title	Fast active learning for pure exploration in reinforcement learning
name	citation_author	Pierre Ménard
name	citation_author	Omar Darwiche Domingues
name	citation_author	Émilie Kaufmann
name	citation_author	Anders Jonsson
name	citation_author	Édouard Leurent
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/menard2021fast.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2007.13442
name	citation_title	Revisiting Peng's Q(λ) for modern reinforcement learning
name	citation_author	Tadashi Kozuno
name	citation_author	Yunhao Tang
name	citation_author	Mark Rowland
name	citation_author	Rémi Munos
name	citation_author	Steven Kapturowski
name	citation_author	Will Dabney
name	citation_author	Michal Valko
name	citation_author	David Abel
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/kozuno2021revisiting.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2103.00107
name	citation_title	Taylor expansion of discount factors
name	citation_author	Yunhao Tang
name	citation_author	Mark Rowland
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/tang2021taylor.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2106.06170
name	citation_title	Online A-optimal design and active linear regression
name	citation_author	Xavier Fontaine
name	citation_author	Pierre Perrault
name	citation_author	Michal Valko
name	citation_author	Vianney Perchet
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/fontaine2021online.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	1906.08509
name	citation_title	Kernel-based reinforcement learning: A finite-time analysis
name	citation_author	Omar Darwiche Domingues
name	citation_author	Pierre Ménard
name	citation_author	Matteo Pirotta
name	citation_author	Émilie Kaufmann
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/domingues2021kernel-based.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2004.05599
name	citation_title	Game plan: What AI can do for football, and what football can do for AI
name	citation_author	Karl Tuyls
name	citation_author	Shayegan Omidshafiei
name	citation_author	Paul Muller
name	citation_author	Zhe Wang
name	citation_author	Jerome Connor
name	citation_author	Daniel Hennes
name	citation_author	Ian Graham
name	citation_author	William Spearman
name	citation_author	Tim Waskett
name	citation_author	Dafydd Steele
name	citation_author	Pauline Luc
name	citation_author	Adrià Recasens
name	citation_author	Alexandre Galashov
name	citation_author	Gregory Thornton
name	citation_author	Romuald Elie
name	citation_author	Pablo Sprechmann
name	citation_author	Pol Moreno
name	citation_author	Kris Cao
name	citation_author	Marta Garnelo
name	citation_author	Praneet Dutta
name	citation_author	Michal Valko
name	citation_author	Nicolas Heess
name	citation_author	Alex Bridgland
name	citation_author	Julien Pérolat
name	citation_author	Bart De Vylder
name	citation_author	Ali Eslami
name	citation_author	Mark Rowland
name	citation_author	Andrew Jaegle
name	citation_author	Rémi Munos
name	citation_author	Trevor Back
name	citation_author	Razia Ahamed
name	citation_author	Simon Bouton
name	citation_author	Nathalie Beauguerlange
name	citation_author	Jackson Broshear
name	citation_author	Thore Graepel
name	citation_author	Demis Hassabis
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/tuyls2021game.pdf
name	citation_journal_title	Journal of Artificial Intelligence Research
name	citation_arxiv_id	2011.09192
name	citation_title	A kernel-based approach to non-stationary reinforcement learning in metric spaces
name	citation_author	Omar Darwiche Domingues
name	citation_author	Pierre Ménard
name	citation_author	Matteo Pirotta
name	citation_author	Émilie Kaufmann
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/domingues2021kernel-based-non-stationary.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	2007.05078
name	citation_title	Episodic reinforcement learning in finite MDPs: Minimax lower bounds revisited
name	citation_author	Omar Darwiche Domingues
name	citation_author	Pierre Ménard
name	citation_author	Émilie Kaufmann
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/domingues2021episodic.pdf
name	citation_conference_title	Algorithmic Learning Theory
name	citation_arxiv_id	2010.03531
name	citation_title	Sample complexity bounds for stochastic shortest path with a generative model
name	citation_author	Jean Tarbouriech
name	citation_author	Matteo Pirotta
name	citation_author	Michal Valko
name	citation_author	Alessandro Lazaric
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/tarbouriech2021sample.pdf
name	citation_conference_title	Algorithmic Learning Theory
name	citation_title	Adaptive reward-free exploration
name	citation_author	Émilie Kaufmann
name	citation_author	Pierre Ménard
name	citation_author	Omar Darwiche Domingues
name	citation_author	Anders Jonsson
name	citation_author	Édouard Leurent
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/kaufmann2021adaptive.pdf
name	citation_conference_title	Algorithmic Learning Theory
name	citation_arxiv_id	2006.06294
name	citation_title	Fast sampling from β-ensembles
name	citation_author	Guillaume Gautier
name	citation_author	Rémi Bardenet
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/gautier2020fast.pdf
name	citation_journal_title	Statistics and Computing
name	citation_arxiv_id	2003.02344
name	citation_title	Mine Your Own vieW: Self-supervised learning through across-sample prediction
name	citation_author	Mehdi Azabou
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Ran Liu
name	citation_author	Chi-Heng Lin
name	citation_author	Erik C. Johnson
name	citation_author	Kiran Bhaskaran-Nair
name	citation_author	Max Dabagia
name	citation_author	Bernardo Ávila Pires
name	citation_author	Lindsey Kitchell
name	citation_author	Keith B. Hengen
name	citation_author	William Gray-Roncal
name	citation_author	Michal Valko
name	citation_author	Eva L. Dyer
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/azabou2021mine.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2102.10106
name	citation_title	Density-based bonuses on learned representations for reward-free exploration in deep reinforcement learning
name	citation_author	Omar Darwiche Domingues
name	citation_author	Corentin Tallec
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/domingues2021density-based.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Geometric entropic exploration
name	citation_author	Zhaohan Daniel Guo
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Alaa Saade
name	citation_author	Shantanu Thakoor
name	citation_author	Bilal Piot
name	citation_author	Bernardo Ávila Pires
name	citation_author	Michal Valko
name	citation_author	Thomas Mesnard
name	citation_author	Tor Lattimore
name	citation_author	Rémi Munos
name	citation_publication_date	2021
name	citation_pdf_url	https://misovalko.github.io/publications/guo2021geometric.pdf
name	citation_journal_title	Journal of Machine Learning Research
name	citation_arxiv_id	2101.02055
name	citation_title	Self-supervised representation learning using bootstrapped latent representations
name	citation_author	Jean-Bastien Grill
name	citation_author	Florian Strub
name	citation_author	Florent Altché
name	citation_author	Corentin Tallec
name	citation_author	Pierre Richemond
name	citation_author	Bernardo Ávila Pires
name	citation_author	Zhaohan Daniel Guo
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Bilal Piot
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2021
name	citation_pdf_url	https://patentimages.storage.googleapis.com/6d/7b/01/520999ec8a3c29/US20210383225A1.pdf
name	citation_title	Bootstrap Your Own Latent: A new approach to self-supervised learning
name	citation_author	Jean-Bastien Grill
name	citation_author	Florian Strub
name	citation_author	Florent Altché
name	citation_author	Corentin Tallec
name	citation_author	Pierre H. Richemond
name	citation_author	Elena Buchatskaya
name	citation_author	Carl Doersch
name	citation_author	Bernardo Ávila Pires
name	citation_author	Zhaohan Daniel Guo
name	citation_author	Mohammad Gheshlaghi Azar
name	citation_author	Bilal Piot
name	citation_author	Koray Kavukcuoglu
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/grill2020bootstrap.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2006.07733
name	citation_title	BYOL works even without batch statistics
name	citation_author	Pierre H. Richemond
name	citation_author	Jean-Bastien Grill
name	citation_author	Florent Altché
name	citation_author	Corentin Tallec
name	citation_author	Florian Strub
name	citation_author	Andrew Brock
name	citation_author	Samuel Smith
name	citation_author	Soham De
name	citation_author	Razvan Pascanu
name	citation_author	Bilal Piot
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/richemond2020byol.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2010.10241
name	citation_title	Improved sample complexity for incremental autonomous exploration in MDPs
name	citation_author	Jean Tarbouriech
name	citation_author	Matteo Pirotta
name	citation_author	Michal Valko
name	citation_author	Alessandro Lazaric
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/tarbouriech2020improved.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2012.14755
name	citation_title	Sampling from a k-DPP without looking at all items
name	citation_author	Daniele Calandriello*
name	citation_author	Michał Dereziński*
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2020sampling.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2006.16947
name	citation_title	Statistical efficiency of Thompson sampling for combinatorial semi-bandits
name	citation_author	Pierre Perrault
name	citation_author	Étienne Boursier
name	citation_author	Vianney Perchet
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/perrault2020statistical.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2006.06613
name	citation_title	Planning in Markov decision processes with gap-dependent sample complexity
name	citation_author	Anders Jonsson
name	citation_author	Émilie Kaufmann
name	citation_author	Pierre Ménard
name	citation_author	Omar Darwiche Domingues
name	citation_author	Édouard Leurent
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/jonsson2020planning.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2006.05879
name	citation_title	Monte-Carlo tree search as regularized policy optimization
name	citation_author	Jean-Bastien Grill
name	citation_author	Florent Altché
name	citation_author	Yunhao Tang
name	citation_author	Thomas Hubert
name	citation_author	Michal Valko
name	citation_author	Ioannis Antonoglou
name	citation_author	Rémi Munos
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/grill2020monte-carlo.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2007.12509
name	citation_title	Taylor expansion policy optimization
name	citation_author	Yunhao Tang
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/tang2020taylor.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2003.06259
name	citation_title	Gamification of pure exploration for linear bandits
name	citation_author	Rémy Degenne
name	citation_author	Pierre Ménard
name	citation_author	Xuedong Shang
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/degenne2020gamification.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2007.00953
name	citation_title	Budgeted online influence maximization
name	citation_author	Pierre Perrault
name	citation_author	Zheng Wen
name	citation_author	Jennifer Healey
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/perrault2020budgeted.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	No-regret exploration in goal-oriented reinforcement learning
name	citation_author	Jean Tarbouriech
name	citation_author	Evrard Garcelon
name	citation_author	Michal Valko
name	citation_author	Matteo Pirotta
name	citation_author	Alessandro Lazaric
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/tarbouriech2020no-regret.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	1912.03517
name	citation_title	Improved sleeping bandits with stochastic action sets and adversarial rewards
name	citation_author	Aadirupa Saha
name	citation_author	Pierre Gaillard
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/saha2020improved.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2004.06248
name	citation_title	Stochastic bandits with arm-dependent delays
name	citation_author	Anne Manegueu
name	citation_author	Claire Vernade
name	citation_author	Alexandra Carpentier
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/manegueu2020stochastic.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2006.10459
name	citation_title	Near-linear time Gaussian process optimization with adaptive batching and resparsification
name	citation_author	Daniele Calandriello
name	citation_author	Luigi Carratino
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_author	Lorenzo Rosasco
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2020near-linear.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2002.09954
name	citation_title	Covariance-adapting algorithm for semi-bandits with application to sparse rewards
name	citation_author	Pierre Perrault
name	citation_author	Vianney Perchet
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/perrault2020covariance-adapting.pdf
name	citation_conference_title	Conference on Learning Theory
name	citation_arxiv_id	2604.13738
name	citation_title	Fixed-confidence guarantees for Bayesian best-arm identification
name	citation_author	Xuedong Shang
name	citation_author	Rianne de Heide
name	citation_author	Émilie Kaufmann
name	citation_author	Pierre Ménard
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/shang2020fixed-confidence.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	1910.10945
name	citation_title	Adaptive multi-fidelity optimization with fast learning rates
name	citation_author	Côme Fiegel
name	citation_author	Victor Gabillon
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/fiegel2020adaptive.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_title	Derivative-free & order-robust optimisation
name	citation_author	Victor Gabillon
name	citation_author	Rasul Tutunov
name	citation_author	Haitham Bou Ammar
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/gabillon2020derivative-free.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	1910.04034
name	citation_title	A single algorithm for both restless and rested rotting bandits
name	citation_author	Julien Seznec
name	citation_author	Pierre Ménard
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/seznec2020single.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_title	Reward-free exploration beyond finite-horizon
name	citation_author	Jean Tarbouriech
name	citation_author	Matteo Pirotta
name	citation_author	Michal Valko
name	citation_author	Alessandro Lazaric
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/tarbouriech2020reward-free.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Spectral bandits
name	citation_author	Tomáš Kocák
name	citation_author	Rémi Munos
name	citation_author	Branislav Kveton
name	citation_author	Shipra Agrawal
name	citation_author	Michal Valko
name	citation_publication_date	2020
name	citation_pdf_url	https://misovalko.github.io/publications/kocak2020spectral.pdf
name	citation_journal_title	Journal of Machine Learning Research
name	citation_arxiv_id	2604.25272
name	citation_title	Planning in entropy-regularized Markov decision processes and games
name	citation_author	Jean-Bastien Grill*
name	citation_author	Omar Darwiche Domingues*
name	citation_author	Pierre Ménard
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/grill2019planning.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_title	Multiagent evaluation under incomplete information
name	citation_author	Mark Rowland
name	citation_author	Shayegan Omidshafiei
name	citation_author	Karl Tuyls
name	citation_author	Julien Pérolat
name	citation_author	Michal Valko
name	citation_author	Georgios Piliouras
name	citation_author	Rémi Munos
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/rowland2019multiagent.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	1909.09849
name	citation_title	Exact sampling of determinantal point processes with sublinear time preprocessing
name	citation_author	Michał Dereziński*
name	citation_author	Daniele Calandriello*
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/derezinski2019exact.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	1905.13476
name	citation_title	On two ways to use determinantal point processes for Monte Carlo integration
name	citation_author	Guillaume Gautier
name	citation_author	Rémi Bardenet
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/gautier2019two.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_title	Gaussian process optimization with adaptive sketching: Scalable and no regret
name	citation_author	Daniele Calandriello
name	citation_author	Luigi Carratino
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_author	Lorenzo Rosasco
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2019gaussian.pdf
name	citation_conference_title	Conference on Learning Theory
name	citation_arxiv_id	1903.05594
name	citation_title	Scale-free adaptive planning for deterministic dynamics & discounted rewards
name	citation_author	Peter Bartlett
name	citation_author	Victor Gabillon
name	citation_author	Jennifer Healey
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/bartlett2019scale-free.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Exploiting structure of uncertainty for efficient matroid semi-bandits
name	citation_author	Pierre Perrault
name	citation_author	Vianney Perchet
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/perrault2019exploiting.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	1902.03794
name	citation_title	A simple dynamic bandit-based algorithm for hyper-parameter tuning
name	citation_author	Xuedong Shang
name	citation_author	Émilie Kaufmann
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/shang2019simple.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	DPPy: Sampling determinantal point processes with Python
name	citation_author	Guillaume Gautier
name	citation_author	Guillermo Polito
name	citation_author	Rémi Bardenet
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/gautier2019dppy.pdf
name	citation_journal_title	Journal of Machine Learning Research
name	citation_arxiv_id	1809.07258
name	citation_title	Rotting bandits are not harder than stochastic ones
name	citation_author	Julien Seznec
name	citation_author	Andrea Locatelli
name	citation_author	Alexandra Carpentier
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/seznec2019rotting.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	1811.11043
name	citation_title	Active multiple matrix completion with adaptive confidence sets
name	citation_author	Andrea Locatelli
name	citation_author	Alexandra Carpentier
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/locatelli2019active.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_title	Finding the bandit in a graph: Sequential search-and-stop
name	citation_author	Pierre Perrault
name	citation_author	Vianney Perchet
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/perrault2019finding.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	1806.02282
name	citation_title	A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption
name	citation_author	Peter L. Bartlett
name	citation_author	Victor Gabillon
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/bartlett2019simple.pdf
name	citation_conference_title	Algorithmic Learning Theory
name	citation_arxiv_id	1810.00997
name	citation_title	General parallel optimization without metric
name	citation_author	Xuedong Shang
name	citation_author	Émilie Kaufmann
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/shang2019general.pdf
name	citation_conference_title	Algorithmic Learning Theory
name	citation_title	Les processus ponctuels déterminantaux en apprentissage automatique
name	citation_author	Guillaume Gautier
name	citation_author	Rémi Bardenet
name	citation_author	Michal Valko
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/gautier2019processus.pdf
name	citation_title	Optimizing human learning workshop eliciting adaptive sequences for learning (WeASeL)
name	citation_author	Fabrice Popineau
name	citation_author	Michal Valko
name	citation_author	Jill-Jênn Vie
name	citation_publication_date	2019
name	citation_pdf_url	https://misovalko.github.io/publications/popineau2019optimizing.pdf
name	citation_title	Optimistic optimization of a Brownian
name	citation_author	Jean-Bastien Grill
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_publication_date	2018
name	citation_pdf_url	https://misovalko.github.io/publications/grill2018optimistic.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	1901.04884
name	citation_title	Adaptive black-box optimization got easier: HCT needs only local smoothness
name	citation_author	Xuedong Shang
name	citation_author	Émilie Kaufmann
name	citation_author	Michal Valko
name	citation_publication_date	2018
name	citation_pdf_url	https://misovalko.github.io/publications/shang2018adaptive.pdf
name	citation_conference_title	European Workshop on Reinforcement Learning
name	citation_title	Compressing the input for CNNs with the first-order scattering transform
name	citation_author	Édouard Oyallon
name	citation_author	Eugene Belilovsky
name	citation_author	Sergey Zagoruyko
name	citation_author	Michal Valko
name	citation_publication_date	2018
name	citation_pdf_url	https://misovalko.github.io/publications/oyallon2018compressing.pdf
name	citation_conference_title	European Conference on Computer Vision
name	citation_arxiv_id	1809.10200
name	citation_title	Improved large-scale graph learning through ridge spectral sparsification
name	citation_author	Daniele Calandriello
name	citation_author	Ioannis Koutis
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2018
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2018improved.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Best of both worlds: Stochastic & adversarial best-arm identification
name	citation_author	Yasin Abbasi-Yadkori
name	citation_author	Peter L. Bartlett
name	citation_author	Victor Gabillon
name	citation_author	Alan Malek
name	citation_author	Michal Valko
name	citation_publication_date	2018
name	citation_pdf_url	https://misovalko.github.io/publications/abbasi-yadkori2018best.pdf
name	citation_conference_title	Conference on Learning Theory
name	citation_title	Efficient second-order online kernel learning with adaptive embedding
name	citation_author	Daniele Calandriello
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2017
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2017efficient.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_title	Online influence maximization under independent cascade model with semi-bandit feedback
name	citation_author	Zheng Wen
name	citation_author	Branislav Kveton
name	citation_author	Michal Valko
name	citation_author	Sharan Vaswani
name	citation_publication_date	2017
name	citation_pdf_url	https://misovalko.github.io/publications/wen2017online.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	1605.06593
name	citation_title	Second-order kernel online convex optimization with adaptive sketching
name	citation_author	Daniele Calandriello
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2017
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2017second.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	1706.04892
name	citation_title	Zonotope hit-and-run for efficient sampling from projection DPPs
name	citation_author	Guillaume Gautier
name	citation_author	Rémi Bardenet
name	citation_author	Michal Valko
name	citation_publication_date	2017
name	citation_pdf_url	https://misovalko.github.io/publications/gautier2017zonotope.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	1705.10498
name	citation_title	Distributed adaptive sampling for kernel matrix approximation
name	citation_author	Daniele Calandriello
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2017
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2017distributed.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	1803.10172
name	citation_title	Trading off rewards and errors in multi-armed bandits
name	citation_author	Akram Erraqabi
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_author	Emma Brunskill
name	citation_author	Yu-En Liu
name	citation_publication_date	2017
name	citation_pdf_url	https://misovalko.github.io/publications/erraqabi2017trading.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_title	Bandits on graphs and structures
name	citation_author	Michal Valko
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/valko2016bandits.pdf
name	citation_title	Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning
name	citation_author	Jean-Bastien Grill
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/grill2016blazing.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_title	Pack only the essentials: Adaptive dictionary learning for kernel ridge regression
name	citation_author	Daniele Calandriello
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2016pack.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_title	Rewards and errors in multi-armed bandit for interactive education
name	citation_author	Akram Erraqabi
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_author	Emma Brunskill
name	citation_author	Yu-En Liu
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/erraqabi2016rewards.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_title	Pliable rejection sampling
name	citation_author	Akram Erraqabi
name	citation_author	Michal Valko
name	citation_author	Alexandra Carpentier
name	citation_author	Odalric-Ambrym Maillard
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/erraqabi2016pliable.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Analysis of Nyström method with sequential ridge leverage scores
name	citation_author	Daniele Calandriello
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2016analysis.pdf
name	citation_conference_title	Uncertainty in Artificial Intelligence
name	citation_title	Online learning with Erdős-Rényi side-observation graphs
name	citation_author	Tomáš Kocák
name	citation_author	Gergely Neu
name	citation_author	Michal Valko
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/kocak2016onlinea.pdf
name	citation_conference_title	Uncertainty in Artificial Intelligence
name	citation_arxiv_id	2604.25271
name	citation_title	Bayesian policy gradient and actor-critic algorithms
name	citation_author	Mohammad Ghavamzadeh
name	citation_author	Yaakov Engel
name	citation_author	Michal Valko
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/ghavamzadeh2016bayesian.pdf
name	citation_journal_title	Journal of Machine Learning Research
name	citation_arxiv_id	2604.27563
name	citation_title	Online learning with noisy side observations
name	citation_author	Tomáš Kocák
name	citation_author	Gergely Neu
name	citation_author	Michal Valko
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/kocak2016online.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	2604.13740
name	citation_title	Revealing graph bandits for maximizing local influence
name	citation_author	Alexandra Carpentier
name	citation_author	Michal Valko
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/carpentier2016revealing.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_title	Analysis of Kelner and Levin graph sparsification algorithm for a streaming setting
name	citation_author	Daniele Calandriello
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2016
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2016kelner.pdf
name	citation_arxiv_id	1609.03769
name	citation_title	Incremental spectral sparsification for large-scale graph-based semi-supervised learning
name	citation_author	Daniele Calandriello
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_author	Ioannis Koutis
name	citation_publication_date	2016
name	citation_pdf_url	https://arxiv.org/pdf/1601.05675.pdf
name	citation_arxiv_id	1601.05675
name	citation_title	Black-box optimization of noisy functions with unknown smoothness
name	citation_author	Jean-Bastien Grill
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_publication_date	2015
name	citation_pdf_url	https://misovalko.github.io/publications/grill2015black-box.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_title	Simple regret for infinitely many armed bandits
name	citation_author	Alexandra Carpentier
name	citation_author	Michal Valko
name	citation_publication_date	2015
name	citation_pdf_url	https://misovalko.github.io/publications/carpentier2015simple.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	1505.04627
name	citation_title	Cheap bandits
name	citation_author	Manjesh Hanawal
name	citation_author	Venkatesh Saligrama
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_publication_date	2015
name	citation_pdf_url	https://misovalko.github.io/publications/hanawal2015cheap.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	1506.04782
name	citation_title	Large-scale semi-supervised learning with online spectral graph sparsification
name	citation_author	Daniele Calandriello
name	citation_author	Alessandro Lazaric
name	citation_author	Michal Valko
name	citation_publication_date	2015
name	citation_pdf_url	https://misovalko.github.io/publications/calandriello2015large-scale.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2604.26550
name	citation_title	Maximum entropy semi-supervised inverse reinforcement learning
name	citation_author	Julien Audiffren
name	citation_author	Michal Valko
name	citation_author	Alessandro Lazaric
name	citation_author	Mohammad Ghavamzadeh
name	citation_publication_date	2015
name	citation_pdf_url	https://misovalko.github.io/publications/audiffren2015maximum.pdf
name	citation_conference_title	International Joint Conference on Artificial Intelligence
name	citation_title	Efficient learning by implicit exploration in bandit problems with side observations
name	citation_author	Tomáš Kocák
name	citation_author	Gergely Neu
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_publication_date	2014
name	citation_pdf_url	https://misovalko.github.io/publications/kocak2014efficient.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2604.24555
name	citation_title	Extreme bandits
name	citation_author	Alexandra Carpentier
name	citation_author	Michal Valko
name	citation_publication_date	2014
name	citation_pdf_url	https://misovalko.github.io/publications/carpentier2014extreme.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2604.24545
name	citation_title	Online combinatorial optimization with stochastic decision sets and adversarial losses
name	citation_author	Gergely Neu
name	citation_author	Michal Valko
name	citation_publication_date	2014
name	citation_pdf_url	https://misovalko.github.io/publications/neu2014online.pdf
name	citation_conference_title	Neural Information Processing Systems
name	citation_arxiv_id	2604.25269
name	citation_title	Spectral bandits for smooth graph functions
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_author	Branislav Kveton
name	citation_author	Tomáš Kocák
name	citation_publication_date	2014
name	citation_pdf_url	https://misovalko.github.io/publications/valko2014spectral.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Spectral Thompson sampling
name	citation_author	Tomáš Kocák
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_author	Shipra Agrawal
name	citation_publication_date	2014
name	citation_pdf_url	https://misovalko.github.io/publications/kocak2014spectral.pdf
name	citation_conference_title	AAAI Conference on Artificial Intelligence
name	citation_arxiv_id	2604.13739
name	citation_title	Bandits attack function optimization
name	citation_author	Philippe Preux
name	citation_author	Rémi Munos
name	citation_author	Michal Valko
name	citation_publication_date	2014
name	citation_pdf_url	https://misovalko.github.io/publications/preux2014bandits.pdf
name	citation_title	Spectral bandits for smooth graph functions with applications in recommender systems
name	citation_author	Tomáš Kocák
name	citation_author	Michal Valko
name	citation_author	Rémi Munos
name	citation_author	Branislav Kveton
name	citation_author	Shipra Agrawal
name	citation_publication_date	2014
name	citation_pdf_url	https://misovalko.github.io/publications/kocak2014wspectral.pdf
name	citation_conference_title	AAAI Conference on Artificial Intelligence
name	citation_arxiv_id	2605.20552
name	citation_title	Stochastic simultaneous optimistic optimization
name	citation_author	Michal Valko
name	citation_author	Alexandra Carpentier
name	citation_author	Rémi Munos
name	citation_publication_date	2013
name	citation_pdf_url	https://misovalko.github.io/publications/valko2013stochastic.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_arxiv_id	2604.24537
name	citation_title	Finite-time analysis of kernelised contextual bandits
name	citation_author	Michal Valko
name	citation_author	Nathan Korda
name	citation_author	Rémi Munos
name	citation_author	Ilias Flaounas
name	citation_author	Nello Cristianini
name	citation_publication_date	2013
name	citation_pdf_url	https://misovalko.github.io/publications/valko2013finite.pdf
name	citation_conference_title	Uncertainty in Artificial Intelligence
name	citation_arxiv_id	1309.6869
name	citation_title	Learning from a single labeled face and a stream of unlabeled data
name	citation_author	Branislav Kveton
name	citation_author	Michal Valko
name	citation_publication_date	2013
name	citation_pdf_url	https://misovalko.github.io/publications/kveton2013learning.pdf
name	citation_arxiv_id	2604.27564
name	citation_title	Outlier detection for patient monitoring and alerting
name	citation_author	Miloš Hauskrecht
name	citation_author	Iyad Batal
name	citation_author	Michal Valko
name	citation_author	Shyam Visweswaran
name	citation_author	Gregory F. Cooper
name	citation_author	Gilles Clermont
name	citation_publication_date	2013
name	citation_pdf_url	https://misovalko.github.io/publications/hauskrecht2013outlier.pdf
name	citation_title	Semi-supervised apprenticeship learning
name	citation_author	Michal Valko
name	citation_author	Mohammad Ghavamzadeh
name	citation_author	Alessandro Lazaric
name	citation_publication_date	2012
name	citation_pdf_url	https://misovalko.github.io/publications/valko2012semi-supervised.pdf
name	citation_conference_title	European Workshop on Reinforcement Learning
name	citation_title	Conditional anomaly detection with soft harmonic functions
name	citation_author	Michal Valko
name	citation_author	Branislav Kveton
name	citation_author	Hamed Valizadegan
name	citation_author	Gregory F. Cooper
name	citation_author	Miloš Hauskrecht
name	citation_publication_date	2011
name	citation_pdf_url	https://misovalko.github.io/publications/valko2011conditionala.pdf
name	citation_conference_title	IEEE International Conference on Data Mining
name	citation_title	Identification of microbial and proteomic biomarkers in early childhood caries
name	citation_author	Thomas C. Hart
name	citation_author	Patricia M. Corby
name	citation_author	Miloš Hauskrecht
name	citation_author	Ok Hee Ryu
name	citation_author	Richard Pelikan
name	citation_author	Michal Valko
name	citation_author	Maria B. Oliveira
name	citation_author	Gerald T. Hoehn
name	citation_author	Walter A. Bretz
name	citation_publication_date	2011
name	citation_pdf_url	https://misovalko.github.io/publications/hart2011indentification.pdf
name	citation_title	Adaptive graph-based algorithms for conditional anomaly detection and semi-supervised learning
name	citation_author	Michal Valko
name	citation_publication_date	2011
name	citation_pdf_url	https://misovalko.github.io/publications/valko2011adaptive.pdf
name	citation_title	Conditional anomaly detection using soft harmonic functions: An application to clinical alerting
name	citation_author	Michal Valko
name	citation_author	Hamed Valizadegan
name	citation_author	Branislav Kveton
name	citation_author	Gregory F. Cooper
name	citation_author	Miloš Hauskrecht
name	citation_publication_date	2011
name	citation_pdf_url	https://misovalko.github.io/publications/valko2011conditional.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Online semi-supervised learning on quantized graphs
name	citation_author	Michal Valko
name	citation_author	Branislav Kveton
name	citation_author	Ling Huang
name	citation_author	Daniel Ting
name	citation_publication_date	2010
name	citation_pdf_url	https://misovalko.github.io/publications/valko2010online.pdf
name	citation_conference_title	Uncertainty in Artificial Intelligence
name	citation_arxiv_id	1203.3522
name	citation_title	Semi-supervised learning with max-margin graph cuts
name	citation_author	Branislav Kveton
name	citation_author	Michal Valko
name	citation_author	Ali Rahimi
name	citation_author	Ling Huang
name	citation_publication_date	2010
name	citation_pdf_url	https://misovalko.github.io/publications/kveton2010semi-supervised.pdf
name	citation_conference_title	International Conference on Artificial Intelligence and Statistics
name	citation_arxiv_id	2604.26818
name	citation_title	Conditional outlier detection for clinical alerting
name	citation_author	Miloš Hauskrecht
name	citation_author	Michal Valko
name	citation_author	Shyam Visweswaran
name	citation_author	Iyad Batal
name	citation_author	Gilles Clermont
name	citation_author	Gregory Cooper
name	citation_publication_date	2010
name	citation_pdf_url	https://misovalko.github.io/publications/hauskrecht2010conditional.pdf
name	citation_conference_title	Annual American Medical Informatics Association Conference
name	citation_title	Online semi-supervised perception: Real-time learning without explicit feedback
name	citation_author	Branislav Kveton
name	citation_author	Michal Valko
name	citation_author	Matthai Phillipose
name	citation_author	Ling Huang
name	citation_publication_date	2010
name	citation_pdf_url	https://misovalko.github.io/publications/kveton2010online.pdf
name	citation_conference_title	IEEE Conference on Computer Vision and Pattern Recognition
name	citation_arxiv_id	2604.27562
name	citation_title	Feature importance analysis for patient management decisions
name	citation_author	Michal Valko
name	citation_author	Miloš Hauskrecht
name	citation_publication_date	2010
name	citation_pdf_url	https://misovalko.github.io/publications/valko2010feature.pdf
name	citation_title	Conditional anomaly detection methods for patient-management alert systems
name	citation_author	Michal Valko
name	citation_author	Gregory Cooper
name	citation_author	Amy Seybert
name	citation_author	Shyam Visweswaran
name	citation_author	Melissa Saul
name	citation_author	Miloš Hauskrecht
name	citation_publication_date	2008
name	citation_pdf_url	https://misovalko.github.io/publications/valko2008conditional.pdf
name	citation_conference_title	International Conference on Machine Learning
name	citation_title	Distance metric learning for conditional anomaly detection
name	citation_author	Michal Valko
name	citation_author	Miloš Hauskrecht
name	citation_publication_date	2008
name	citation_pdf_url	https://misovalko.github.io/publications/valko2008distance.pdf
name	citation_conference_title	Florida Artificial Intelligence Research Society Conference
name	citation_title	Learning predictive models for combinations of heterogeneous proteomic data sources
name	citation_author	Michal Valko
name	citation_author	Richard Pelikan
name	citation_author	Miloš Hauskrecht
name	citation_publication_date	2008
name	citation_pdf_url	https://misovalko.github.io/publications/valko2008learning.pdf
name	citation_conference_title	Annual American Medical Informatics Association Conference
name	citation_title	Evidence-based anomaly detection in clinical domains
name	citation_author	Miloš Hauskrecht
name	citation_author	Michal Valko
name	citation_author	Branislav Kveton
name	citation_author	Shyam Visweswaran
name	citation_author	Gregory Cooper
name	citation_publication_date	2007
name	citation_pdf_url	https://misovalko.github.io/publications/hauskrecht2007evidence-based.pdf
name	citation_conference_title	Annual American Medical Informatics Association Conference
name	citation_title	A comparison of chief complaints and emergency department reports for identifying patients with acute lower respiratory syndrome
name	citation_author	Wendy W. Chapman
name	citation_author	John N. Dowling
name	citation_author	Gregory F. Cooper
name	citation_author	Miloš Hauskrecht
name	citation_author	Michal Valko
name	citation_publication_date	2006
name	citation_pdf_url	https://misovalko.github.io/publications/chapman2006comparison.pdf
name	citation_title	Feature selection and dimensionality reduction in genomics and proteomics
name	citation_author	Miloš Hauskrecht
name	citation_author	Richard Pelikan
name	citation_author	Michal Valko
name	citation_author	James Lyons-Weiler
name	citation_publication_date	2006
name	citation_title	Evolutionary feature selection for spiking neural network pattern classifiers
name	citation_author	Michal Valko
name	citation_author	Nuno C. Marques
name	citation_author	Marco Castelani
name	citation_publication_date	2005
name	citation_pdf_url	https://misovalko.github.io/publications/valko2005evolutionary.pdf
name	citation_arxiv_id	2604.26654
name	citation_title	Evolving neural networks for statistical decision theory
name	citation_author	Michal Valko
name	citation_publication_date	2005
name	citation_pdf_url	https://misovalko.github.io/publications/valko2005evolving.pdf
name	twitter:card	summary_large_image
name	twitter:site	@misovalko
name	twitter:creator	@misovalko
name	twitter:title	Michal Valko - Publications
name	twitter:description	Publications on reinforcement learning, bandits, LLM alignment, and self-supervised learning at NeurIPS, ICML, ICLR, COLT, and AISTATS.
name	twitter:image	https://misovalko.github.io/images/common/mvgr20.webp
name	twitter:image:alt	Photo of Michal Valko
property	og:title	Michal Valko - Publications
property	og:description	Publications on reinforcement learning, bandits, LLM alignment, and self-supervised learning at NeurIPS, ICML, ICLR, COLT, and AISTATS.
property	og:image	https://misovalko.github.io/images/common/mvgr20.webp
property	og:image:width	1200
property	og:image:height	630
property	og:url	https://misovalko.github.io/research.html
property	og:type	website
property	og:locale	en_US
property	og:site_name	Michal Valko
property	og:image:alt	Photo of Michal Valko

Оптимизация Готовность: 80%

Структура

Ошибок нет

Семантические HTML-элементы страницы ?

Структура документа корректна (теги <html> и <body> присутствуют в единственном экземпляре).

Контент

Ошибок нет

Объём и качество текстового содержимого ?

Слова из title 3 встречаются в тексте достаточно.

Абзацев с текстом 164 достаточно.

Среднее число слов в абзаце 144 достаточно.

Кол-во знаков контента 203337 на странице оптимально.

Кол-во слов 29893 на странице оптимально.

Заголовки

Ошибок нет

Иерархия заголовков H1–H6 ?

На странице присутствуют заголовки <h1> 1. Это прекрасно.

На странице присутствуют заголовки <h2> 22. Это хорошо.

Тошнота

16,73

Насколько одно слово доминирует в тексте ?

Тошнота превышает норму 5. Измените текст страницы!

Исправить

Академич. тошнота

83,48%

Насколько текст перенасыщен ключевыми словами ?

Академическая тошнота превышает норму 5-15%. Измените текст страницы!

Исправить

Семантическое ядро

Наиболее часто встречающиеся слова на странице ?

Контент страницы содержит осмысленный текст и слова.

Показать список слов

Слово	Кол-во	Частота
learning	280	0,94%
michal	166	0,56%
abstract	164	0,55%
bibtex	160	0,54%
algorithm	154	0,52%
preprint	109	0,36%
problem	91	0,30%
regret	88	0,29%
algorithms	87	0,29%
policy	83	0,28%
conference	80	0,27%
methods	75	0,25%
international	74	0,25%
setting	73	0,24%
optimization	72	0,24%
exploration	72	0,24%
number	67	0,22%
machine	67	0,22%
reinforcement	66	0,22%
poster	64	0,21%

Индексация Готовность: 0%

Индексирование

Есть ошибки

Разрешено ли индексирование страницы ?

Анкоров на странице 847 слишком много. Проведите ревизию и оптимизацию ссылок сайта.

Исправить

Robots.txt

Найден корректный robots.txt

Файл управления сканированием сайта роботами ?

Robots.txt настроен корректно. Размер файла: 1551 байт. Загружен за: 0сек.

Проверяемая страница не запрещена в robots.txt.

Robots.txt доступен по постоянному адресу

Показать содержимое robots.txt

# robots.txt for misovalko.github.io
# Guide search engine crawlers

User-agent: *
Allow: /

# Disallow crawling of backup and temporary files
Disallow: /website-automation/
Disallow: /scripts/
Disallow: /data/
Disallow: /tmp/
Disallow: /cv/*.log
Disallow: /cv/*.aux
Disallow: /cv/*.out
Disallow: /*.bak$
Disallow: /*~$

# Disallow old/deprecated legacy pages
Disallow: /camera.html
Disallow: /comps.html
Disallow: /fmfi-grades.html
Disallow: /fmfi-timetable.html
Disallow: /fmfi-taken-courses.html
Disallow: /pitt-taken-courses.html
Disallow: /phd-calls.html
Disallow: /phdthesis.html
Disallow: /project-*.html
Disallow: /ta-cs0007-fall2005.html
Disallow: /splash.html
Disallow: /misc.html
Disallow: /musicold.html
Disallow: /oktava2000.html
Disallow: /lisboa.html
Disallow: /glee.html
Disallow: /plasyn.html
Disallow: /soc-inet.html

# Disallow old course materials and archives
Disallow: /projects/courses/
Disallow: /projects/phd_comprehensive_exam/
Disallow: /projects/seminar/
Disallow: /projects/fmfi/
Disallow: /projects/skms/
Disallow: /projects/sav/
Disallow: /projects/stosoo/
Disallow: /projects/ties/

# Allow access to main content
Allow: /images/
Allow: /publications/
Allow: /projects/bandits/
Allow: /projects/mva/

# Allow new content pages
Allow: /collaborate.html
Allow: /coauthors.html

# Allow feeds for discovery
Allow: /feed.xml
Allow: /notes-feed.xml

# Crawl delay for polite crawling
Crawl-delay: 1

# Sitemap locations
Sitemap: https://misovalko.github.io/sitemap.xml
Sitemap: https://misovalko.github.io/sitemap-images.xml

Sitemap

Кол-во: 2

XML-карта сайта для поисковиков ?

Robots.txt содержит несколько карт сайтов 2. Это профессионально!

Robots.txt не содержит ошибок в картах сайта.

Показать карты сайта

Url	Статус
https://misovalko.github.io/sitemap.xml
https://misovalko.github.io/sitemap-images.xml

Внутренние ссылки

Кол-во: 470

Ссылки на другие страницы своего сайта ?

Внутренних ссылок на странице 470 слишком много. Проведите оптимизацию сайта!

Внутренние ссылки не запрещены к индексации в robots.txt.

На странице присутствуют изображения 1.

Показать первые 100 внутренних ссылок

Url	Анкор	Состояние
/index.html	Intro
/research.html	Publications
/projects.html	Projects
/mva-ml-graphs.html	Teaching
/talks.html	Talks
/press.html	Press
/service.html	Service
/collaborate.html	Collaborate
/experience.html	Experience
/publications/all-publications.bib	<svg width="24" height="24" viewbox="0 0 448 512" fill="currentColor"><path d="M64 32C28.7 32 0 60.7 0 96V416c0 35.3 28.7 64 64 64H384c35.3 0 64-28.7 64-64V173.3c0-17-6.7-33.3-18.7-45.3L352 50.7C340 38.7 323.7 32 306.7 32H64zm0 96c0-17.7 14.3-32 32-32H288V144c0 17.7 14.3 32 32 32h48V416c0 17.7-14.3 32-32 32H96c-17.7 0-32-14.3-32-32V128z"></path></svg> Export All BibTeX
/coauthors.html	<svg width="24" height="24" viewbox="0 0 640 512" fill="currentColor"><path d="M144 0a80 80 0 1 1 0 160A80 80 0 1 1 144 0zM512 0a80 80 0 1 1 0 160A80 80 0 1 1 512 0zM0 298.7C0 239.8 47.8 192 106.7 192h42.7c15.9 0 31 3.5 44.6 9.7c-1.3 7.2-1.9 14.7-1.9 22.3c0 38.2 16.8 72.5 43.3 96H21.3C9.6 320 0 310.4 0 298.7zM405.3 320H240c0-26.5 10.5-50.5 27.6-68.2c8.8-9.1 19.3-16.5 30.8-21.8c13.6-6.2 28.7-9.7 44.6-9.7h42.7C426.7 220.3 469.3 267.8 469.3 326.7c0 5.9 0 11.8 0 17.8c-20.5-15.4-45.9-24.2-73.3-24.2H320c0-27.7 11.2-52.8 29.3-71l6-6.2c9.6-9.1 20.7-16.5 33-21.8l14.7 8.8l14.7-8.8c12.3 5.3 23.4 12.7 33 21.8l6 6.2c18.1 18.2 29.3 43.3 29.3 71c0 0 0 .1 0 .1H405.3zM544 128a64 64 0 1 0 -128 0 64 64 0 1 0 128 0zM576 298.7C576 239.8 528.2 192 469.3 192H512c59 0 106.7 47.8 106.7 106.7c0 11.8-9.6 21.3-21.3 21.3H544c26.5 0 50.5-10.5 68.2-27.6c9.1-8.8 16.5-19.3 21.8-30.8l0 0zm-256 0C320 239.8 272.2 192 213.3 192h42.7C315 192 362.7 239.8 362.7 298.7c0 11.8-9.6 21.3-21.3 21.3H277.3c18.2 17.2 43.3 27.6 70.7 27.6c0 0 0 0 0 0c0 38.2-16.8 72.5-43.3 96c0 0 0-.1 0-.1c0-27.7-11.2-52.8-29.3-71l-6-6.2c-9.6-9.1-20.7-16.5-33-21.8z"></path></svg> Co-Author Network
/publications/battleday2026dig.pdf	<em>DiG-bench: Discovery in Games</em>
/publications/battleday2026dig.bib	bibtex
/publications/fiegel2026optimal.pdf	<em>Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier</em>
/publications/fiegel2026optimal.bib	bibtex
/publications/tang2025rlfinetuning.pdf	<em>RL-finetuning LLMs from on- and off-policy data with a single algorithm</em>
/publications/tang2025rlfinetuning.bib	bibtex
/publications/tang2025understanding.pdf	<em>Understanding the performance gap between online and offline alignment algorithms</em>
/publications/tang2024understanding.bib	bibtex
/publications/kveton2016learning.pdf	<em>Learning to act greedily: Polymatroid semi-bandits</em>
/publications/kveton2016learning.bib	bibtex
/publications/scheid2024optimal.arxiv.pdf	<em>Optimal design for reward modeling in RLHF</em>
/publications/scheid2024optimal.bib	bibtex
/publications/perrault2025cumulant.pdf	<em>A new bound on the cumulant generating function of Dirichlet processes</em>
/publications/perrault2024new.bib	bibtex
/publications/belomestny2025sharp.pdf	<em>Sharp deviations bounds for Dirichlet weighted sums with application to analysis of Bayesian algorithms</em>
/publications/belomestny2023sharp.bib	bibtex
/publications/kozuno2025kl.pdf	<em>KL-entropy-regularized RL with a generative model is minimax optimal</em>
/publications/kozuno2022klentropyregularized.bib	bibtex
/publications/perrault2025submodular.pdf	<em>On the approximation relationship between optimizing ratio of submodular (RS) and difference of submodular (DS) functions</em>
/publications/perrault2021approximation.bib	bibtex
/publications/racca2025language.pdf	<em>Language generation with replay: A learning-theoretic view of model collapse</em>
/publications/racca2025language.bib	bibtex
/images/racca2025language-icml2026-poster.png	poster (image)
/publications/fiegel2025harder.pdf	<em>The harder path: Last iterate convergence for uncoupled learning in zero-sum games with bandit feedback</em>
/publications/fiegel2025harder.pdf	PDF
/publications/fiegel2025harder.bib	bibtex
/publications/tiapkin2026accelerating.pdf	<em>Proximal point Nash learning from human feedback</em>
/publications/tiapkin2026accelerating.bib	bibtex
/publications/tiapkin2026accelerating.poster.pdf	poster
/publications/liu2025generation.pdf	<em>Generation of an output token sequence from an input token sequence using two language model neural networks</em>
/publications/wang2025preference.pdf	<em>Preference optimization with multi-sample comparisons</em>
/publications/wang2024preference.bib	bibtex
/publications/llama2024llama3.pdf	<em>The Llama 3 herd of models</em>
/publications/llama2024llama.bib	bibtex
/publications/didolkar2024metacognitive.pdf	<em>Metacognitive capabilities of LLMs: An exploration in mathematical problem solving</em>
/publications/didolkar2024metacognitive.poster.pdf	poster
/publications/didolkar2024metacognitive.bib	bibtex
/publications/fiegel2024local.pdf	<em>Local and adaptive mirror descents in extensive-form games</em>
/publications/fiegel2024local.bib	bibtex
/publications/munos2024nash.pdf	<em>Nash learning from human feedback</em>
/images/munos2024nash_image.webp	image
/publications/munos2024nash.bib	bibtex
/publications/munos2024nash.talk.pdf	talk
/publications/calandriello2024human.pdf	<em>Human alignment of large language models through online preference optimisation</em>
/publications/calandriello2024human.bib	bibtex
/publications/tang2024generalized.pdf	<em>Generalized preference optimization: A unified approach to offline alignment</em>
/publications/tang2024generalized.bib	bibtex
/publications/liu2024decodingtime.pdf	<em>Decoding-time realignment of language models</em>
/publications/liu2024decodingtime.bib	bibtex
/publications/azar2024unified.pdf	<em>A general theoretical paradigm to understand learning from human preferences</em>
/publications/azar2024general.bib	bibtex
/publications/saade2024unlocking.pdf	<em>Unlocking the power of representations in long-term novelty-based exploration</em>
/publications/saade2024unlocking.bib	bibtex
/publications/tiapkin2024demonstrationregularized.pdf	<em>Demonstration-regularized RL</em>
/publications/tiapkin2024demonstrationregularized.bib	bibtex
/publications/domingues2024rlberry.pdf	<em>rlberry: A reinforcement learning library for research and education</em>
/publications/domingues2024rlberry.bib	bibtex
/publications/tiapkin2023model-free.pdf	<em>Model-free posterior sampling via learning rate randomization</em>
/publications/tiapkin2023modelfree.bib	bibtex
/publications/eberhard2023middle-mile.pdf	<em>Middle-mile logistics through the lens of goal-conditioned reinforcement learning</em>
/publications/eberhard2023middlemile.bib	bibtex
/publications/jarrett2022curiosity.pdf	<em>Curiosity in hindsight: Intrinsic exploration in stochastic environments</em>
/images/jarrett2022curiosity_image.webp	image
/publications/jarrett2023curiosity.bib	bibtex
/publications/jarrett2022curiosity.talk.pdf	talk
/publications/tang2023valearning.pdf	<em>VA-learning as a more efficient alternative to Q-learning</em>
/publications/tang2023valearning.bib	bibtex
/publications/tiapkin2023fast.pdf	<em>Fast rates for maximum entropy exploration</em>
/publications/tiapkin2023fast.bib	bibtex
/publications/fiegel2023adapting.pdf	<em>Adapting to game trees in zero-sum imperfect information games</em>
/publications/fiegel2023adapting.poster.pdf	poster
/images/fiegel2023adapting_poster.webp	poster (image)
/publications/fiegel2023adapting.talk.pdf	talk
/publications/fiegel2023adapting.bib	bibtex
/publications/tang2023selfpredictive.pdf	<em>Understanding self-predictive learning for reinforcement learning</em>
/publications/tang2023understanding.bib	bibtex
/publications/tang2023domoac.pdf	<em>DoMo-AC: Doubly multi-step off-policy actor-critic algorithm</em>
/publications/tang2023domoac.bib	bibtex
/publications/kitamura2023regularization.pdf	<em>Regularization and variance-weighted regression achieves minimax optimality in linear MDPs: Theory and practice</em>
/publications/kitamura2023regularization.pdf	pdf
/publications/kitamura2023regularization.bib	bibtex
/publications/mesnard2023quantile.pdf	<em>Quantile credit assignment</em>
/publications/mesnard2023quantile.bib	bibtex
/publications/azabou2023halfhop.pdf	<em>Half-Hop: A graph upsampling approach for slowing down message passing</em>
/publications/azabou2023halfhop.bib	bibtex
/publications/azabou2023half-hop.poster.pdf	poster
/publications/guo2022byol.pdf	<em>BYOL-Explore: Exploration by bootstrapped prediction</em>
/publications/guo2022byol.poster.pdf	poster
/publications/guo2022byolexplore.bib	bibtex

Исправить

Внешние ссылки

Кол-во: 161

Ссылки на сторонние сайты ?

Внешних ссылок на странице 161 слишком много. Спрячьте лишние ссылки в тег noindex или атрибут rel='nofollow'!

Показать первые 100 внешних ссылок

Url	Анкор
scholar.google.com	<svg xmlns="http://www.w3.org/2000/svg" viewbox="0 0 640 512" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M320 32L0 160l320 128 320-128L320 32zM64 224v128l256 128 256-128V224L320 352 64 224z"></path></svg>
orcid.org	<svg xmlns="http://www.w3.org/2000/svg" viewbox="0 0 512 512" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M294.75 188.19h-45.92V342h47.47c67.62 0 83.12-51.34 83.12-76.91 0-41.64-26.54-76.9-84.67-76.9zM256 8C119 8 8 119 8 256s111 248 248 248 248-111 248-248S393 8 256 8zm-80.79 360.76h-29.84v-207.5h29.84zm-14.92-231.14a19.57 19.57 0 1 1 19.57-19.57 19.64 19.64 0 0 1-19.57 19.57zM300 369h-81V143.26h81c62.52 0 113 28.05 113 113.42C413 322.38 364.87 369 300 369z"></path></svg>
github.com	<svg xmlns="http://www.w3.org/2000/svg" viewbox="0 0 496 512" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8z"></path></svg>
linkedin.com	<svg xmlns="http://www.w3.org/2000/svg" viewbox="0 0 448 512" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M100.28 448H7.4V148.9h92.88zM53.79 108.1C24.09 108.1 0 83.5 0 53.8a53.79 53.79 0 0 1 107.58 0c0 29.7-24.1 54.3-53.79 54.3zM447.9 448h-92.68V302.4c0-34.7-.7-79.2-48.29-79.2-48.29 0-55.69 37.7-55.69 76.7V448h-92.78V148.9h89.08v40.8h1.3c12.4-23.5 42.69-48.3 87.88-48.3 94 0 111.28 61.9 111.28 142.3V448z"></path></svg>
x.com	<svg xmlns="http://www.w3.org/2000/svg" viewbox="0 0 512 512" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M389.2 48h70.6L305.6 224.2 487 464H345L233.7 318.6 106.5 464H35.8L200.7 275.5 26.8 48H172.4L272.9 180.9 389.2 48zM364.4 421.8h39.1L151.1 88h-42L364.4 421.8z"></path></svg>
bsky.app	<svg xmlns="http://www.w3.org/2000/svg" viewbox="0 0 16 16" width="1em" height="1em" fill="currentColor" aria-hidden="true"><path d="M3.468 1.948C5.303 3.325 7.276 6.118 8 7.616c.725-1.498 2.698-4.29 4.532-5.668C13.855.955 16 .186 16 2.632c0 .489-.28 4.105-.444 4.692-.572 2.04-2.653 2.561-4.504 2.246 3.236.551 4.06 2.375 2.281 4.2-3.376 3.464-4.852-.87-5.23-1.98-.07-.204-.103-.3-.103-.218 0-.081-.033.014-.102.218-.379 1.11-1.855 5.444-5.231 1.98-1.778-1.825-.955-3.65 2.28-4.2-1.85.315-3.932-.205-4.503-2.246C.28 6.737 0 3.12 0 2.632 0 .186 2.145.955 3.468 1.948"></path></svg>
github.com	GitHub
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
openreview.net	OpenReview
openreview.net	OpenReview
arxiv.org	arXiv preprint
patentimages.storage.googleapis.com	<em>Reinforcement learning using hindsight to model unpredictable aspects of the future</em>
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
github.com	GitHub
patentimages.storage.googleapis.com	<em>Reinforcement learning by directly learning an advantage function</em>
arxiv.org	arXiv preprint
openreview.net	OpenReview preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
proceedings.mlr.press	PMLR proceedings
arxiv.org	arXiv preprint
pytorch-geometric.readthedocs.io	code
patentimages.storage.googleapis.com	<em>Reinforcement learning using density estimation with online clustering for exploration</em>
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
youtu.be	video
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
youtu.be	video
arxiv.org	arXiv preprint
youtu.be	video
youtu.be	video
arxiv.org	arXiv preprint
youtu.be	video 1
youtu.be	video 2
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
openreview.net	OpenReview
urlworkshop.github.io	ICML 2021 Workshop: Unsupervised Reinforcement Learning
arxiv.org	arXiv preprint
patentimages.storage.googleapis.com	<em>Self-supervised representation learning using bootstrapped latent representations</em>
arxiv.org	arXiv preprint
x.com	our X announcement
github.com	our code
youtu.be	YouTube video by Yannic
medium.com	unofficial blog 1
medium.com	unofficial blog 2
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
icml.cc	video
arxiv.org	arXiv preprint
arxiv.org	arXiv preprint
icml.cc	video
arxiv.org	arXiv preprint

Исправить

Конкуренты Готовность: 0%

Конкуренты в Яндексе

Кол-во: 0

Топ сайтов-конкурентов в Яндексе ?

Мы не нашли у вас конкурентов в Яндексе. Сайт или очень молодой или плохо продвигается.

Конкурентов в ТОП-10 Яндекса не нашлось.

Исправить

Конкуренты в Google

Кол-во: 0

Топ сайтов-конкурентов в Google ?

Конкуренты в Google тоже не найдены. Займитесь продвижением сайта!

Конкурентов в ТОП-10 Google не нашлось.

Исправить

ЗоЗПП: права потребителей Готовность: 100%

Нарушения

Не выявлены

Признаков дистанционной продажи товаров (интернет-магазина) не обнаружено — требования ЗоЗПП о раскрытии информации продавца к сайту не применяются. Нарушений нет.

ФЗ-149: рекомендательные технологии Готовность: 100%

Нарушения

Не выявлены

Рекомендательные блоки («с этим покупают», «похожие товары» и т.п.) на сайте не обнаружены — требования ст. 10.7 ФЗ-149 к сайту не применяются. Нарушений нет.

ФЗ-38: реклама Готовность: 100%

Нарушения

Не выявлены

Рекламных тематик с обязательными оговорками (медицина, БАД, кредиты и займы, новостройки) на сайте не обнаружено. Нарушений нет.

ФЗ-436: защита детей Готовность: 100%

Нарушения

Не выявлены

Признаков информационной продукции (новости, видео, книги, игры, курсы) не обнаружено — обязательная возрастная маркировка по ФЗ-436 сайту не требуется. Нарушений нет.

Поделитесь с друзьями:

Анализ страницы https://misovalko.github.io/research.html

Основное Готовность: 90%

Домен

Ответ сервера

Безопасность

Кодировка

Язык

Скорость загрузки

Объем документа

Ресурсы

Серверные заголовки

CMS

Веб-сервер

Мета-теги Готовность: 80%

Title

Description

Keywords

Канонический Url

Robots

Адаптивность

Разметка OpenGraph

Все мета-теги

Оптимизация Готовность: 80%

Структура

Контент

Заголовки

Тошнота

Академич. тошнота

Семантическое ядро

Индексация Готовность: 0%

Индексирование

Robots.txt

Sitemap

Внутренние ссылки

Внешние ссылки

Конкуренты Готовность: 0%

Конкуренты в Яндексе

Конкуренты в Google

ЗоЗПП: права потребителей Готовность: 100%

Нарушения

ФЗ-149: рекомендательные технологии Готовность: 100%

Нарушения

ФЗ-38: реклама Готовность: 100%

Нарушения

ФЗ-436: защита детей Готовность: 100%

Нарушения

Вердикт