Timezone: »
Spotlight
Kernel-Based Reinforcement Learning: A Finite-Time Analysis
Omar Darwiche Domingues · Pierre Menard · Matteo Pirotta · Emilie Kaufmann · Michal Valko
We consider the exploration-exploitation dilemma in finite-horizon reinforcement learning problems whose state-action space is endowed with a metric. We introduce Kernel-UCBVI, a model-based optimistic algorithm that leverages the smoothness of the MDP and a non-parametric kernel estimator of the rewards and transitions to efficiently balance exploration and exploitation. For problems with $K$ episodes and horizon $H$, we provide a regret bound of $\widetilde{O}\left( H^3 K^{\frac{2d}{2d+1}}\right)$, where $d$ is the covering dimension of the joint state-action space. This is the first regret bound for kernel-based RL using smoothing kernels, which requires very weak assumptions on the MDP and applies to a wide range of tasks. We empirically validate our approach in continuous MDPs with sparse rewards.
Author Information
Omar Darwiche Domingues (Inria)
Pierre Menard (Inria)
Matteo Pirotta (Facebook AI Research)
Emilie Kaufmann (CNRS, Univ. Lille, Inria)
Michal Valko (DeepMind / Inria / ENS Paris-Saclay)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: Kernel-Based Reinforcement Learning: A Finite-Time Analysis »
Wed. Jul 21st 04:00 -- 06:00 PM Room None
More from the Same Authors
-
2021 : Marginalized Operators for Off-Policy Reinforcement Learning »
Yunhao Tang · Mark Rowland · Remi Munos · Michal Valko -
2021 : Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection »
Matteo Papini · Andrea Tirinzoni · Aldo Pacchiano · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 : A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs »
Andrea Tirinzoni · Matteo Pirotta · Alessandro Lazaric -
2021 : Bridging The Gap between Local and Joint Differential Privacy in RL »
Evrard Garcelon · Vianney Perchet · Ciara Pike-Burke · Matteo Pirotta -
2021 : Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret »
Jean Tarbouriech · Jean Tarbouriech · Simon Du · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2021 : Density-Based Bonuses on Learned Representations for Reward-Free Exploration in Deep Reinforcement Learning »
Omar Darwiche Domingues · Corentin Tallec · Remi Munos · Michal Valko -
2022 Oral: From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses »
Daniil Tiapkin · Denis Belomestny · Eric Moulines · Alexey Naumov · Sergey Samsonov · Yunhao Tang · Michal Valko · Pierre MENARD -
2022 Spotlight: Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times »
Daniele Calandriello · Luigi Carratino · Alessandro Lazaric · Michal Valko · Lorenzo Rosasco -
2022 Spotlight: Retrieval-Augmented Reinforcement Learning »
Anirudh Goyal · Abe Friesen Friesen · Andrea Banino · Theophane Weber · Nan Rosemary Ke · Adrià Puigdomenech Badia · Arthur Guez · Mehdi Mirza · Peter Humphreys · Ksenia Konyushkova · Michal Valko · Simon Osindero · Timothy Lillicrap · Nicolas Heess · Charles Blundell -
2022 : Emilie Kaufmann »
Emilie Kaufmann -
2022 Workshop: Responsible Decision Making in Dynamic Environments »
Virginie Do · Thorsten Joachims · Alessandro Lazaric · Joelle Pineau · Matteo Pirotta · Harsh Satija · Nicolas Usunier -
2022 Poster: From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses »
Daniil Tiapkin · Denis Belomestny · Eric Moulines · Alexey Naumov · Sergey Samsonov · Yunhao Tang · Michal Valko · Pierre MENARD -
2022 Poster: Retrieval-Augmented Reinforcement Learning »
Anirudh Goyal · Abe Friesen Friesen · Andrea Banino · Theophane Weber · Nan Rosemary Ke · Adrià Puigdomenech Badia · Arthur Guez · Mehdi Mirza · Peter Humphreys · Ksenia Konyushkova · Michal Valko · Simon Osindero · Timothy Lillicrap · Nicolas Heess · Charles Blundell -
2022 Poster: Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times »
Daniele Calandriello · Luigi Carratino · Alessandro Lazaric · Michal Valko · Lorenzo Rosasco -
2021 : Invited Speaker: Emilie Kaufmann: On pure-exploration in Markov Decision Processes »
Emilie Kaufmann -
2021 Poster: Leveraging Good Representations in Linear Contextual Bandits »
Matteo Papini · Andrea Tirinzoni · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 Poster: Optimal Thompson Sampling strategies for support-aware CVaR bandits »
Dorian Baudry · Romain Gautron · Emilie Kaufmann · Odalric-Ambrym Maillard -
2021 Spotlight: Leveraging Good Representations in Linear Contextual Bandits »
Matteo Papini · Andrea Tirinzoni · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 Spotlight: Optimal Thompson Sampling strategies for support-aware CVaR bandits »
Dorian Baudry · Romain Gautron · Emilie Kaufmann · Odalric-Ambrym Maillard -
2021 Poster: Fast active learning for pure exploration in reinforcement learning »
Pierre MENARD · Omar Darwiche Domingues · Anders Jonsson · Emilie Kaufmann · Edouard Leurent · Michal Valko -
2021 Poster: UCB Momentum Q-learning: Correcting the bias without forgetting »
Pierre MENARD · Omar Darwiche Domingues · Xuedong Shang · Michal Valko -
2021 Spotlight: Fast active learning for pure exploration in reinforcement learning »
Pierre MENARD · Omar Darwiche Domingues · Anders Jonsson · Emilie Kaufmann · Edouard Leurent · Michal Valko -
2021 Oral: UCB Momentum Q-learning: Correcting the bias without forgetting »
Pierre MENARD · Omar Darwiche Domingues · Xuedong Shang · Michal Valko -
2021 Poster: Online A-Optimal Design and Active Linear Regression »
Xavier Fontaine · Pierre Perrault · Michal Valko · Vianney Perchet -
2021 Spotlight: Online A-Optimal Design and Active Linear Regression »
Xavier Fontaine · Pierre Perrault · Michal Valko · Vianney Perchet -
2021 Poster: Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning »
Tadashi Kozuno · Yunhao Tang · Mark Rowland · Remi Munos · Steven Kapturowski · Will Dabney · Michal Valko · David Abel -
2021 Poster: Taylor Expansion of Discount Factors »
Yunhao Tang · Mark Rowland · Remi Munos · Michal Valko -
2021 Spotlight: Taylor Expansion of Discount Factors »
Yunhao Tang · Mark Rowland · Remi Munos · Michal Valko -
2021 Spotlight: Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning »
Tadashi Kozuno · Yunhao Tang · Mark Rowland · Remi Munos · Steven Kapturowski · Will Dabney · Michal Valko · David Abel -
2020 : Short Talk 3 - A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces »
Omar Darwiche Domingues -
2020 Poster: Monte-Carlo Tree Search as Regularized Policy Optimization »
Jean-Bastien Grill · Florent Altché · Yunhao Tang · Thomas Hubert · Michal Valko · Ioannis Antonoglou · Remi Munos -
2020 Poster: Improved Sleeping Bandits with Stochastic Action Sets and Adversarial Rewards »
Aadirupa Saha · Pierre Gaillard · Michal Valko -
2020 Poster: No-Regret Exploration in Goal-Oriented Reinforcement Learning »
Jean Tarbouriech · Evrard Garcelon · Michal Valko · Matteo Pirotta · Alessandro Lazaric -
2020 Poster: Gamification of Pure Exploration for Linear Bandits »
Rémy Degenne · Pierre Menard · Xuedong Shang · Michal Valko -
2020 Poster: Stochastic bandits with arm-dependent delays »
Anne Gael Manegueu · Claire Vernade · Alexandra Carpentier · Michal Valko -
2020 Poster: Budgeted Online Influence Maximization »
Pierre Perrault · Jennifer Healey · Zheng Wen · Michal Valko -
2020 Poster: Near-linear time Gaussian process optimization with adaptive batching and resparsification »
Daniele Calandriello · Luigi Carratino · Alessandro Lazaric · Michal Valko · Lorenzo Rosasco -
2020 Poster: Taylor Expansion Policy Optimization »
Yunhao Tang · Michal Valko · Remi Munos