Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions

3 October 2020

Papers citing "Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions"

31 / 31 papers shown

Title
The Central Role of the Loss Function in Reinforcement Learning Kaiwen Wang Nathan Kallus Wen Sun OffRL 64 7 0 19 Sep 2024
Horizon-Free Regret for Linear Markov Decision Processes Zihan Zhang Jason D. Lee Yuxin Chen Simon S. Du 33 3 0 15 Mar 2024
When is Agnostic Reinforcement Learning Statistically Tractable? Zeyu Jia Gene Li Alexander Rakhlin Ayush Sekhari Nathan Srebro OffRL 34 5 0 09 Oct 2023
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation Philip Amortila Nan Jiang Csaba Szepesvári OffRL 31 3 0 25 Jul 2023
Exponential Hardness of Reinforcement Learning with Linear Function Approximation Daniel M. Kane Sihan Liu Shachar Lovett G. Mahajan Csaba Szepesvári Gellert Weisz 46 3 0 25 Feb 2023
Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning Volodymyr Tkachuk Seyed Alireza Bakhtiari Johannes Kirschner Matej Jusup Ilija Bogunovic Csaba Szepesvári 32 5 0 08 Feb 2023
Linear Reinforcement Learning with Ball Structure Action Space Zeyu Jia Randy Jia Dhruv Madeka Dean Phillips Foster 31 1 0 14 Nov 2022
When is Realizability Sufficient for Off-Policy Reinforcement Learning? Andrea Zanette OffRL 24 14 0 10 Nov 2022
A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games Wei Xiong Han Zhong Chengshuai Shi Cong Shen Tong Zhang 66 18 0 04 Oct 2022
Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model Gen Li Yuejie Chi Yuting Wei Yuxin Chen 37 18 0 22 Aug 2022
A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation Philip Amortila Nan Jiang Dhruv Madeka Dean Phillips Foster 29 5 0 18 Jul 2022
On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL Jinglin Chen Aditya Modi A. Krishnamurthy Nan Jiang Alekh Agarwal 38 25 0 21 Jun 2022
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information Yonathan Efroni Dylan J. Foster Dipendra Kumar Misra A. Krishnamurthy John Langford OffRL 31 25 0 09 Jun 2022
Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning Andrea Zanette Martin J. Wainwright OOD 45 5 0 01 Jun 2022
A Complete Characterization of Linear Estimators for Offline Policy Evaluation Juan C. Perdomo A. Krishnamurthy Peter L. Bartlett Sham Kakade OffRL 29 3 0 08 Mar 2022
Retrieval-Augmented Reinforcement Learning Anirudh Goyal A. Friesen Andrea Banino T. Weber Nan Rosemary Ke ... Michal Valko Simon Osindero Timothy Lillicrap N. Heess Charles Blundell OffRL 32 53 0 17 Feb 2022
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation Dylan J. Foster A. Krishnamurthy D. Simchi-Levi Yunzong Xu OffRL 21 62 0 21 Nov 2021
Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection Matteo Papini Andrea Tirinzoni Aldo Pacchiano Marcello Restelli A. Lazaric Matteo Pirotta 19 18 0 27 Oct 2021
Representation Learning for Online and Offline RL in Low-rank MDPs Masatoshi Uehara Xuezhou Zhang Wen Sun OffRL 67 127 0 09 Oct 2021
Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning Andrea Zanette Martin J. Wainwright Emma Brunskill OffRL 34 115 0 19 Aug 2021
Efficient Local Planning with Linear Function Approximation Dong Yin Botao Hao Yasin Abbasi-Yadkori N. Lazić Csaba Szepesvári 32 19 0 12 Aug 2021
Bellman-consistent Pessimism for Offline Reinforcement Learning Tengyang Xie Ching-An Cheng Nan Jiang Paul Mineiro Alekh Agarwal OffRL LRM 27 271 0 13 Jun 2021
The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces Chi Jin Qinghua Liu Tiancheng Yu 26 50 0 07 Jun 2021
Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting Gen Li Yuxin Chen Yuejie Chi Yuantao Gu Yuting Wei OffRL 26 28 0 17 May 2021
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation Andrea Zanette Ching-An Cheng Alekh Agarwal 32 53 0 24 Mar 2021
An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap Yuanhao Wang Ruosong Wang Sham Kakade OffRL 39 43 0 23 Mar 2021
Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms Chi Jin Qinghua Liu Sobhan Miryoosefi OffRL 38 215 0 01 Feb 2021
Fast Rates for the Regret of Offline Reinforcement Learning Yichun Hu Nathan Kallus Masatoshi Uehara OffRL 24 30 0 31 Jan 2021
Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP Zihan Zhang Jiaqi Yang Xiangyang Ji S. Du 71 38 0 29 Jan 2021
Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL Andrea Zanette OffRL 26 71 0 14 Dec 2020
Global Optimality Guarantees For Policy Gradient Methods Jalaj Bhandari Daniel Russo 39 186 0 05 Jun 2019