Timezone: »
We study the problem of representation learning in stochastic contextual linear bandits. While the primary concern in this domain is usually to find \textit{realizable} representations (i.e., those that allow predicting the reward function at any context-action pair exactly), it has been recently shown that representations with certain spectral properties (called \textit{HLS}) may be more effective for the exploration-exploitation task, enabling \textit{LinUCB} to achieve constant (i.e., horizon-independent) regret. In this paper, we propose \textsc{BanditSRL}, a representation learning algorithm that combines a novel constrained optimization problem to learn a realizable representation with good spectral properties with a generalized likelihood ratio test to exploit the recovered representation and avoid excessive exploration. We prove that \textsc{BanditSRL} can be paired with any no-regret algorithm and achieve constant regret whenever an \textit{HLS} representation is available. Furthermore, \textsc{BanditSRL} can be easily combined with deep neural networks and we show how regularizing towards \textit{HLS} representations is beneficial in standard benchmarks.
Author Information
Andrea Tirinzoni (Meta AI)
Matteo Papini (Universitat Pompeu Fabra)
Ahmed Touati (Facebook)
Alessandro Lazaric (Facebook Artificial Intelligence Research)
Matteo Pirotta (META)
More from the Same Authors
-
2021 Spotlight: Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret »
Jean Tarbouriech · Runlong Zhou · Simon Du · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2021 Spotlight: A Provably Efficient Sample Collection Strategy for Reinforcement Learning »
Jean Tarbouriech · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2023 : Score-Models for Offline Goal-Conditioned Reinforcement Learning »
Harshit Sushil Sikchi · Rohan Chitnis · Ahmed Touati · Alborz Geramifard · Amy Zhang · Scott Niekum -
2023 : Fast Imitation via Behavior Foundation Models »
Matteo Pirotta · Andrea Tirinzoni · Ahmed Touati · Alessandro Lazaric · Yann Ollivier -
2023 : Fast Imitation via Behavior Foundation Models »
Matteo Pirotta · Andrea Tirinzoni · Ahmed Touati · Alessandro Lazaric · Yann Ollivier -
2023 Poster: A State Representation for Diminishing Rewards »
Ted Moskovitz · Samo Hromadka · Ahmed Touati · Diana Borsa · Maneesh Sahani -
2022 Poster: Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits »
Gergely Neu · Julia Olkhovskaya · Matteo Papini · Ludovic Schwartz -
2022 Poster: Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs »
Andrea Tirinzoni · Aymen Al Marjani · Emilie Kaufmann -
2022 Poster: On Elimination Strategies for Bandit Fixed-Confidence Identification »
Andrea Tirinzoni · Rémy Degenne -
2021 Poster: Local Differential Privacy for Regret Minimization in Reinforcement Learning »
Evrard Garcelon · Vianney Perchet · Ciara Pike-Burke · Matteo Pirotta -
2021 Poster: Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret »
Jean Tarbouriech · Runlong Zhou · Simon Du · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2021 Poster: A Provably Efficient Sample Collection Strategy for Reinforcement Learning »
Jean Tarbouriech · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2021 Poster: Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection »
Matteo Papini · Andrea Tirinzoni · Aldo Pacchiano · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta -
2021 Poster: Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification »
Clémence Réda · Andrea Tirinzoni · Rémy Degenne -
2020 Poster: An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Bandits »
Andrea Tirinzoni · Matteo Pirotta · Marcello Restelli · Alessandro Lazaric -
2020 Poster: Adversarial Attacks on Linear Contextual Bandits »
Evrard Garcelon · Baptiste Roziere · Laurent Meunier · Jean Tarbouriech · Olivier Teytaud · Alessandro Lazaric · Matteo Pirotta -
2020 Poster: Improved Sample Complexity for Incremental Autonomous Exploration in MDPs »
Jean Tarbouriech · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2020 Poster: Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration »
Andrea Zanette · Alessandro Lazaric · Mykel J Kochenderfer · Emma Brunskill -
2020 Oral: Improved Sample Complexity for Incremental Autonomous Exploration in MDPs »
Jean Tarbouriech · Matteo Pirotta · Michal Valko · Alessandro Lazaric -
2019 : Poster Session »
Ahana Ghosh · Javad Shafiee · Akhilan Boopathy · Alex Tamkin · Theodoros Vasiloudis · Vedant Nanda · Ali Baheri · Paul Fieguth · Andrew Bennett · Guanya Shi · Hao Liu · Arushi Jain · Jacob Tyo · Benjie Wang · Boxiao Chen · Carroll Wainwright · Chandramouli Shama Sastry · Chao Tang · Daniel S. Brown · David Inouye · David Venuto · Dhruv Ramani · Dimitrios Diochnos · Divyam Madaan · Dmitrii Krashenikov · Joel Oren · Doyup Lee · Eleanor Quint · elmira amirloo · Matteo Pirotta · Gavin Hartnett · Geoffroy Dubourg-Felonneau · Gokul Swamy · Pin-Yu Chen · Ilija Bogunovic · Jason Carter · Javier Garcia-Barcos · Jeet Mohapatra · Jesse Zhang · Jian Qian · John Martin · Oliver Richter · Federico Zaiter · Wentao Weng · Karthik Abinav Sankararaman · Kyriakos Polymenakos · Lan Hoang · mahdieh abbasi · Marco Gallieri · Mathieu Seurin · Matteo Papini · Matteo Turchetta · Matthew Sotoudeh · Mehrdad Hosseinzadeh · Nathan Fulton · Masatoshi Uehara · Niranjani Prasad · Oana-Maria Camburu · Patrik Kolaric · Philipp Renz · Prateek Jaiswal · Reazul Hasan Russel · Riashat Islam · Rishabh Agarwal · Alexander Aldrick · Sachin Vernekar · Sahin Lale · Sai Kiran Narayanaswami · Samuel Daulton · Sanjam Garg · Sebastian East · Shun Zhang · Soheil Dsidbari · Justin Goodwin · Victoria Krakovna · Wenhao Luo · Wesley Chung · Yuanyuan Shi · Yuh-Shyang Wang · Hongwei Jin · Ziping Xu -
2019 Poster: Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs »
Jian QIAN · Ronan Fruit · Matteo Pirotta · Alessandro Lazaric -
2019 Poster: A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning »
Nicolas Carion · Nicolas Usunier · Gabriel Synnaeve · Alessandro Lazaric -
2019 Spotlight: A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning »
Nicolas Carion · Nicolas Usunier · Gabriel Synnaeve · Alessandro Lazaric -
2019 Poster: Limiting Extrapolation in Linear Approximate Value Iteration »
Andrea Zanette · Alessandro Lazaric · Mykel J Kochenderfer · Emma Brunskill -
2019 Poster: Regret Bounds for Learning State Representations in Reinforcement Learning »
Ronald Ortner · Matteo Pirotta · Alessandro Lazaric · Ronan Fruit · Odalric-Ambrym Maillard -
2018 Poster: Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes »
Andrea Tirinzoni · Marek Petrik · Xiangli Chen · Brian Ziebart -
2018 Spotlight: Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes »
Andrea Tirinzoni · Marek Petrik · Xiangli Chen · Brian Ziebart -
2018 Poster: Policy Optimization via Importance Sampling »
Alberto Maria Metelli · Matteo Papini · Francesco Faccio · Marcello Restelli -
2018 Poster: Transfer of Value Functions via Variational Methods »
Andrea Tirinzoni · Rafael Rodriguez Sanchez · Marcello Restelli -
2018 Oral: Policy Optimization via Importance Sampling »
Alberto Maria Metelli · Matteo Papini · Francesco Faccio · Marcello Restelli -
2018 Poster: Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes »
Ronan Fruit · Matteo Pirotta · Alessandro Lazaric -
2018 Spotlight: Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes »
Ronan Fruit · Matteo Pirotta · Alessandro Lazaric -
2017 Poster: Compatible Reward Inverse Reinforcement Learning »
Alberto Maria Metelli · Matteo Pirotta · Marcello Restelli -
2017 Poster: Regret Minimization in MDPs with Options without Prior Knowledge »
Ronan Fruit · Matteo Pirotta · Alessandro Lazaric · Emma Brunskill -
2017 Poster: Adaptive Batch Size for Safe Policy Gradients »
Matteo Papini · Matteo Pirotta · Marcello Restelli -
2017 Spotlight: Regret Minimization in MDPs with Options without Prior Knowledge »
Ronan Fruit · Matteo Pirotta · Alessandro Lazaric · Emma Brunskill -
2013 Poster: Adaptive Step-Size for Policy Gradient Methods »
Matteo Pirotta · Marcello Restelli · Luca Bascetta