Skip to yearly menu bar Skip to main content


(109 events)   Timezone:  
Show all
The 2021 schedule is still incomplete
Toggle Poster Visibility
Sat Jul 24 09:00 AM -- 09:25 AM (PDT)
Invited Speaker: Emilie Kaufmann: On pure-exploration in Markov Decision Processes
In Workshop on Reinforcement Learning Theory
Emilie Kaufmann
Sat Jul 24 09:30 AM -- 09:55 AM (PDT)
Invited Speaker: Christian Kroer: Recent Advances in Iterative Methods for Large-Scale Game Solving
In Workshop on Reinforcement Learning Theory
Christian Kroer
Sat Jul 24 10:00 AM -- 10:12 AM (PDT)
Sparsity in the Partially Controllable LQR
In Workshop on Reinforcement Learning Theory
Yonathan Efroni · Sham Kakade · Akshay Krishnamurthy · Cyril Zhang
Sat Jul 24 10:15 AM -- 10:27 AM (PDT)
On the Theory of Reinforcement Learning with Once-per-Episode Feedback
In Workshop on Reinforcement Learning Theory
Niladri Chatterji · Aldo Pacchiano · Peter Bartlett · Michael Jordan
Sat Jul 24 10:30 AM -- 10:42 AM (PDT)
Implicit Finite-Horizon Approximation for Stochastic Shortest Path
In Workshop on Reinforcement Learning Theory
Liyu Chen · Mehdi Jafarnia · Rahul Jain · Haipeng Luo
Sat Jul 24 10:45 AM -- 10:57 AM (PDT)
Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Andrea Zanette · Martin Wainwright · Emma Brunskill
Sat Jul 24 11:00 AM -- 11:25 AM (PDT)
Invited Speaker: Animashree Anandkumar: Stability-aware reinforcement learning in dynamical systems
In Workshop on Reinforcement Learning Theory
Animashree Anandkumar
Sat Jul 24 11:30 AM -- 11:55 AM (PDT)
Invited Speaker: Shie Mannor: Lenient Regret
In Workshop on Reinforcement Learning Theory
Shie Mannor
Sat Jul 24 12:00 PM -- 12:30 PM (PDT)
Social Session
In Workshop on Reinforcement Learning Theory
Sat Jul 24 12:30 PM -- 02:00 PM (PDT)
Poster Session - I
In Workshop on Reinforcement Learning Theory
Sat Jul 24 02:00 PM -- 02:25 PM (PDT)
Invited Speaker: Bo Dai: Leveraging Non-uniformity in Policy Gradient
In Workshop on Reinforcement Learning Theory
Bo Dai
Sat Jul 24 02:30 PM -- 02:55 PM (PDT)
Invited Speaker: Qiaomin Xie: Reinforcement Learning for Zero-Sum Markov Games Using Function Approximation and Correlated Equilibrium
In Workshop on Reinforcement Learning Theory
Qiaomin Xie
Sat Jul 24 03:00 PM -- 03:12 PM (PDT)
Bad-Policy Density: A Measure of Reinforcement-Learning Hardness
In Workshop on Reinforcement Learning Theory
David Abel · Cameron Allen · Dilip Arumugam · D Ellis Hershkowitz · Michael L. Littman · Lawson Wong
Sat Jul 24 03:15 PM -- 03:27 PM (PDT)
Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
In Workshop on Reinforcement Learning Theory
Yu Bai · Chi Jin · Huan Wang · Caiming Xiong
Sat Jul 24 03:30 PM -- 03:42 PM (PDT)
Solving Multi-Arm Bandit Using a Few Bits of Communication
In Workshop on Reinforcement Learning Theory
Osama Hanna · Lin Yang · Christina Fragouli
Sat Jul 24 03:45 PM -- 03:57 PM (PDT)
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee
In Workshop on Reinforcement Learning Theory
Tengyu Xu · Yingbin LIANG · Guanghui Lan
Sat Jul 24 04:00 PM -- 04:25 PM (PDT)
Invited Speaker: Art Owen: Empirical likelihood for reinforcement learning
In Workshop on Reinforcement Learning Theory
Sat Jul 24 04:30 PM -- 05:00 PM (PDT)
Panel Session: Animashree Anandkumar, Christian Kroer, Art Owen, Qiaomin Xie
In Workshop on Reinforcement Learning Theory
Sat Jul 24 05:00 PM -- 05:30 PM (PDT)
Social Session
In Workshop on Reinforcement Learning Theory
Sat Jul 24 05:30 PM -- 09:00 PM (PDT)
Poster Session - II
In Workshop on Reinforcement Learning Theory
Sparsity in the Partially Controllable LQR
In Workshop on Reinforcement Learning Theory
Yonathan Efroni · Sham Kakade · Akshay Krishnamurthy · Cyril Zhang
Multi-Task Offline Reinforcement Learning with Conservative Data Sharing
In Workshop on Reinforcement Learning Theory
Tianhe (Kevin) Yu · Aviral Kumar · Yevgen Chebotar · Karol Hausman · Sergey Levine · Chelsea Finn
Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms
In Workshop on Reinforcement Learning Theory
Chi Jin · Qinghua Liu · Sobhan Miryoosefi
Bridging The Gap between Local and Joint Differential Privacy in RL
In Workshop on Reinforcement Learning Theory
Evrard Garcelon · Vianney Perchet · Ciara Pike-Burke · Matteo Pirotta
Learning Pareto-Optimal Policies in Low-Rank Cooperative Markov Games
In Workshop on Reinforcement Learning Theory
Abhimanyu Dubey · Alex `Sandy' Pentland
The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces
In Workshop on Reinforcement Learning Theory
Chi Jin · Qinghua Liu · Tiancheng Yu
Model-based Offline Reinforcement Learning with Local Misspecification
In Workshop on Reinforcement Learning Theory
Kefan Dong · Ramtin Keramati · Emma Brunskill
Reward-Weighted Regression Converges to a Global Optimum
In Workshop on Reinforcement Learning Theory
Francesco Faccio · Rupesh Kumar Srivastava · Jürgen Schmidhuber
Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Chenjia Bai · Lingxiao Wang · Lei Han · Jianye Hao · Animesh Garg · Peng Liu · Zhaoran Wang
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection
In Workshop on Reinforcement Learning Theory
Matteo Papini · Andrea Tirinzoni · Aldo Pacchiano · Marcello Restelli · Alessandro Lazaric · Matteo Pirotta
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games
In Workshop on Reinforcement Learning Theory
Stefanos Leonardos · Will Overman · Ioannis Panageas · Georgios Piliouras
Marginalized Operators for Off-Policy Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Yunhao Tang · Mark Rowland · Remi Munos · Michal Valko
Online Sub-Sampling for Reinforcement Learning with General Function Approximation
In Workshop on Reinforcement Learning Theory
Dingwen Kong · Ruslan Salakhutdinov · Ruosong Wang · Lin Yang
Mixture of Step Returns in Bootstrapped DQN
In Workshop on Reinforcement Learning Theory
PoHan Chiang · Hsuan-Kung Yang · Zhang-Wei Hong · Chun-Yi Lee
CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee
In Workshop on Reinforcement Learning Theory
Tengyu Xu · Yingbin LIANG · Guanghui Lan
Provably Efficient Multi-Task Reinforcement Learning with Model Transfer
In Workshop on Reinforcement Learning Theory
Chicheng Zhang · Zhi Wang
Estimating Optimal Policy Value in Linear Contextual Bandits beyond Gaussianity
In Workshop on Reinforcement Learning Theory
Jonathan Lee · Weihao Kong · Aldo Pacchiano · Vidya Muthukumar · Emma Brunskill
Mind the Gap: Safely Bridging Offline and Online Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Wanqiao Xu · Kan Xu · Hamsa Bastani · Osbert Bastani
Finite time analysis of temporal difference learning with linear function approximation: the tail averaged case
In Workshop on Reinforcement Learning Theory
Gandharv Patil · Prashanth L.A. · Doina Precup
Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses
In Workshop on Reinforcement Learning Theory
Haipeng Luo · Chen-Yu Wei · Chung-Wei Lee
Value-Based Deep Reinforcement Learning Requires Explicit Regularization
In Workshop on Reinforcement Learning Theory
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine
Non-Stationary Representation Learning in Sequential Multi-Armed Bandits
In Workshop on Reinforcement Learning Theory
Qin Yuzhen · Tommaso Menara · Samet Oymak · ShiNung Ching · Fabio Pasqualetti
Identification and Adaptive Control of Markov Jump Systems: Sample Complexity and Regret Bounds
In Workshop on Reinforcement Learning Theory
Yahya Sattar · Zhe Du · Davoud Ataee Tarzanagh · Necmiye Ozay · Laura Balzano · Samet Oymak
Meta Learning MDPs with linear transition models
In Workshop on Reinforcement Learning Theory
Robert Müller · Aldo Pacchiano · Jack Parker-Holder
A Boosting Approach to Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Nataly Brukhim · Elad Hazan · Karan Singh
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics
In Workshop on Reinforcement Learning Theory
Yonathan Efroni · Dipendra Misra · Akshay Krishnamurthy · Alekh Agarwal · John Langford
Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings
In Workshop on Reinforcement Learning Theory
Shunshi Zhang · Murat Erdogdu · Animesh Garg
Topological Experience Replay for Fast Q-Learning
In Workshop on Reinforcement Learning Theory
Zhang-Wei Hong · Tao Chen · Yen-Chen Lin · Joni Pajarinen · Pulkit Agrawal
A Short Note on the Relationship of Information Gain and Eluder Dimension
In Workshop on Reinforcement Learning Theory
Kaixuan Huang · Sham Kakade · Jason Lee · Qi Lei
Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs
In Workshop on Reinforcement Learning Theory
Jiafan He · Dongruo Zhou · Quanquan Gu
Robust online control with model misspecification
In Workshop on Reinforcement Learning Theory
Xinyi Chen · Udaya Ghai · Elad Hazan · Alexandre Megretsky
Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Tengyang Xie · Nan Jiang · Huan Wang · Caiming Xiong · Yu Bai
A functional mirror ascent view of policy gradient methods with function approximation
In Workshop on Reinforcement Learning Theory
Sharan Vaswani · Olivier Bachem · Simone Totaro · Matthieu Geist · Marlos C. Machado · Pablo Samuel Castro · Nicolas Le Roux
Invariant Policy Learning: A Causal Perspective
In Workshop on Reinforcement Learning Theory
Sorawit Saengkyongam · Nikolaj Thams · Jonas Peters · Niklas Pfister
Learning Nash Equilibria in Zero-Sum Stochastic Games via Entropy-Regularized Policy Approximation
In Workshop on Reinforcement Learning Theory
Yue Guan · Qifan Zhang · Panagiotis Tsiotras
A Spectral Approach to Off-Policy Evaluation for POMDPs
In Workshop on Reinforcement Learning Theory
Yash Nair · Nan Jiang
Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret
In Workshop on Reinforcement Learning Theory
Jean Tarbouriech · Jean Tarbouriech · Simon Du · Matteo Pirotta · Michal Valko · Alessandro Lazaric
Provably efficient exploration-free transfer RL for near-deterministic latent dynamics
In Workshop on Reinforcement Learning Theory
Yao Liu · Dipendra Misra · Miroslav Dudik · Robert Schapire
Nearly Optimal Regret for Learning Adversarial MDPs with Linear Function Approximation
In Workshop on Reinforcement Learning Theory
Jiafan He · Dongruo Zhou · Quanquan Gu
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction
In Workshop on Reinforcement Learning Theory
Ming Yin · Yu Bai · Yu-Xiang Wang
Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings
In Workshop on Reinforcement Learning Theory
Ming Yin · Yu-Xiang Wang
Model-Free Approach to Evaluate Reinforcement Learning Algorithms
In Workshop on Reinforcement Learning Theory
Denis Belomestny · Ilya Levin · Eric Moulines · Alexey Naumov · Sergey Samsonov · Veronika Zorina
Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits
In Workshop on Reinforcement Learning Theory
Wenshuo Guo · Kumar Agrawal · Aditya Grover · Vidya Muthukumar · Ashwin Pananjady
Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
In Workshop on Reinforcement Learning Theory
Yue Wu · Dongruo Zhou · Quanquan Gu
Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation
In Workshop on Reinforcement Learning Theory
Semih Cayci · Niao He · R Srikant
Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature
In Workshop on Reinforcement Learning Theory
Kefan Dong · Jiaqi Yang · Tengyu Ma
Online Learning for Stochastic Shortest Path Model via Posterior Sampling
In Workshop on Reinforcement Learning Theory
Mehdi Jafarnia · Liyu Chen · Rahul Jain · Haipeng Luo
Randomized Least Squares Policy Optimization
In Workshop on Reinforcement Learning Theory
Haque Ishfaq · Zhuoran Yang · Andrei Lupu · Viet Nguyen · Lewis Liu · Riashat Islam · Zhaoran Wang · Doina Precup
Statistical Inference with M-Estimators on Adaptively Collected Data
In Workshop on Reinforcement Learning Theory
Kelly Zhang · Lucas Janson · Susan Murphy
Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
In Workshop on Reinforcement Learning Theory
Dibya Ghosh · Jad Rahme · Aviral Kumar · Amy Zhang · Ryan P. Adams · Sergey Levine
Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure
In Workshop on Reinforcement Learning Theory
Aviv Rosenberg · Yishay Mansour
Optimal and instance-dependent oracle inequalities for policy evaluation
In Workshop on Reinforcement Learning Theory
Wenlong Mou · Ashwin Pananjady · Martin Wainwright
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
In Workshop on Reinforcement Learning Theory
Dhruv Malik · Aldo Pacchiano · Vishwak Srinivasan · Yuanzhi Li
Learning to Observe with Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Mehmet Koseoglu · Ece Kunduracioglu · Ayca Ozcelikkale
The Importance of Non-Markovianity in Maximum State Entropy Exploration
In Workshop on Reinforcement Learning Theory
Mirco Mutti · Riccardo De Santi · Marcello Restelli
Finite-Sample Analysis of Off-Policy Natural Actor-Critic With Linear Function Approximation
In Workshop on Reinforcement Learning Theory
Zaiwei Chen · sajad khodadadian · Siva Maguluri
When Is Generalizable Reinforcement Learning Tractable?
In Workshop on Reinforcement Learning Theory
Dhruv Malik · Yuanzhi Li · Pradeep Ravikumar
Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity
In Workshop on Reinforcement Learning Theory
Kaiqing Zhang · Xiangyuan Zhang · Bin Hu · Tamer Basar
Nonstationary Reinforcement Learning with Linear Function Approximation
In Workshop on Reinforcement Learning Theory
Huozhi Zhou · Jinglin Chen · Lav Varshney · Ashish Jagmohan
On Overconservatism in Offline Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Karush Suri · Florian Shkurti
Collision Resolution in Multi-player Bandits Without Observing Collision Information
In Workshop on Reinforcement Learning Theory
Eleni Nisioti · Nikolaos Thomos · Boris Bellalta · Anders Jonsson
Subgaussian Importance Sampling for Off-Policy Evaluation and Learning
In Workshop on Reinforcement Learning Theory
Alberto Maria Metelli · Alessio Russo · Marcello Restelli
Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks
In Workshop on Reinforcement Learning Theory
Tang Thanh Nguyen · Sunil Gupta · Hung Tran-The · Svetha Venkatesh
Triple-Q: A Model-Free Algorithm for Constrained Reinforcement Learning with Sublinear Regret and Zero Constraint Violation
In Workshop on Reinforcement Learning Theory
Honghao Wei · Xin Liu · Lei Ying
Minimax Regret for Stochastic Shortest Path
In Workshop on Reinforcement Learning Theory
Alon Cohen · Yonathan Efroni · Yishay Mansour · Aviv Rosenberg
Finding the Near Optimal Policy via Reductive Regularization in MDPs
In Workshop on Reinforcement Learning Theory
Wenhao Yang · Xiang Li · Guangzeng Xie · Zhihua Zhang
Finite Sample Analysis of Average-Reward TD Learning and $Q$-Learning
In Workshop on Reinforcement Learning Theory
Sheng Zhang · Zhe Zhang · Siva Maguluri
A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs
In Workshop on Reinforcement Learning Theory
Andrea Tirinzoni · Matteo Pirotta · Alessandro Lazaric
Refined Policy Improvement Bounds for MDPs
In Workshop on Reinforcement Learning Theory
Mark Gluzman
Efficient Inverse Reinforcement Learning of Transferable Rewards
In Workshop on Reinforcement Learning Theory
Giorgia Ramponi · Alberto Maria Metelli · Marcello Restelli
On the Sample Complexity of Average-reward MDPs
In Workshop on Reinforcement Learning Theory
Yujia Jin
Learning Stackelberg Equilibria in Sequential Price Mechanisms
In Workshop on Reinforcement Learning Theory
Gianluca Brero
Improved Estimator Selection for Off-Policy Evaluation
In Workshop on Reinforcement Learning Theory
George Tucker
Comparison and Unification of Three Regularization Methods in Batch Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Sarah Rathnam
Bagged Critic for Continuous Control
In Workshop on Reinforcement Learning Theory
Payal Bawa
A general sample complexity analysis of vanilla policy gradient
In Workshop on Reinforcement Learning Theory
Rui Yuan · Robert Gower · Alessandro Lazaric
Is Pessimism Provably Efficient for Offline RL?
In Workshop on Reinforcement Learning Theory
Ying Jin · Zhuoran Yang · Zhaoran Wang
Almost Optimal Algorithms for Two-player Markov Games with Linear Function Approximation
In Workshop on Reinforcement Learning Theory
Zixiang Chen · Dongruo Zhou · Quanquan Gu
The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition
In Workshop on Reinforcement Learning Theory
Tiancheng Jin · Longbo Huang · Haipeng Luo
Decentralized Q-Learning in Zero-sum Markov Games
In Workshop on Reinforcement Learning Theory
Kaiqing Zhang · David Leslie · Tamer Basar · Asuman Ozdaglar
Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators
In Workshop on Reinforcement Learning Theory
Zaiwei Chen · Siva Maguluri · Sanjay Shakkottai · Karthikeyan Shanmugam
Learning Adversarial Markov Decision Processes with Delayed Feedback
In Workshop on Reinforcement Learning Theory
Tal Lancewicki · Aviv Rosenberg · Yishay Mansour
On the Theory of Reinforcement Learning with Once-per-Episode Feedback
In Workshop on Reinforcement Learning Theory
Niladri Chatterji · Aldo Pacchiano · Peter Bartlett · Michael Jordan
Implicit Finite-Horizon Approximation for Stochastic Shortest Path
In Workshop on Reinforcement Learning Theory
Liyu Chen · Mehdi Jafarnia · Rahul Jain · Haipeng Luo
Bad-Policy Density: A Measure of Reinforcement-Learning Hardness
In Workshop on Reinforcement Learning Theory
David Abel · Cameron Allen · Dilip Arumugam · D Ellis Hershkowitz · Michael L. Littman · Lawson Wong
Gap-Dependent Unsupervised Exploration for Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Jingfeng Wu · Vladimir Braverman · Lin Yang
Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
In Workshop on Reinforcement Learning Theory
Yu Bai · Chi Jin · Huan Wang · Caiming Xiong
Solving Multi-Arm Bandit Using a Few Bits of Communication
In Workshop on Reinforcement Learning Theory
Osama Hanna · Lin Yang · Christina Fragouli
Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning
In Workshop on Reinforcement Learning Theory
Andrea Zanette · Martin Wainwright · Emma Brunskill