v1v2 (latest)

A Sharp Analysis of Model-based Reinforcement Learning with Self-Play

International Conference on Machine Learning (ICML), 2020

4 October 2020

Papers citing "A Sharp Analysis of Model-based Reinforcement Learning with Self-Play"

46 / 96 papers shown

Title
Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium C. J. Li Dongruo Zhou Quanquan Gu Sai Li 139 2 0 10 Aug 2022
Regret Minimization and Convergence to Equilibria in General-sum Markov GamesInternational Conference on Machine Learning (ICML), 2022 Liad Erez Tal Lancewicki Uri Sherman Tomer Koren Yishay Mansour 255 33 0 28 Jul 2022
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured TransitionsInternational Conference on Machine Learning (ICML), 2022 Delin Qu Xiaohan Wei Jieping Ye Zhaoran Wang Zhuoran Yang OffRL 150 11 0 25 Jul 2022
A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games Zihan Ding DiJia Su Qinghua Liu Chi Jin 221 3 0 18 Jul 2022
Interaction Pattern Disentangling for Multi-Agent Reinforcement LearningIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 Shunyu Liu Mingli Song Yihe Zhou Na Yu Kaixuan Chen Zunlei Feng Weilong Dai 286 16 0 08 Jul 2022
On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RLNeural Information Processing Systems (NeurIPS), 2022 Jinglin Chen Aditya Modi A. Krishnamurthy Nan Jiang Alekh Agarwal 279 28 0 21 Jun 2022
Policy Optimization for Markov Games: Unified Framework and Faster ConvergenceNeural Information Processing Systems (NeurIPS), 2022 Runyu Zhang Qinghua Liu Haiquan Wang Caiming Xiong Na Li Yu Bai 366 30 0 06 Jun 2022
Learning in Congestion Games with Bandit FeedbackNeural Information Processing Systems (NeurIPS), 2022 Qiwen Cui Zhihan Xiong Maryam Fazel S. Du 184 16 0 04 Jun 2022
Sample-Efficient Reinforcement Learning of Partially Observable Markov GamesNeural Information Processing Systems (NeurIPS), 2022 Qinghua Liu Csaba Szepesvári Chi Jin 258 27 0 02 Jun 2022
Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise BonusNeural Information Processing Systems (NeurIPS), 2022 Qiwen Cui S. Du OffRL 149 23 0 01 Jun 2022
Scalable Multi-Agent Model-Based Reinforcement LearningAdaptive Agents and Multi-Agent Systems (AAMAS), 2022 Vladimir Egorov A. Shpilman 156 39 0 25 May 2022
The Complexity of Markov Equilibrium in Stochastic GamesAnnual Conference Computational Learning Theory (COLT), 2022 C. Daskalakis Noah Golowich Jianchao Tan 135 69 0 08 Apr 2022
Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium ComputationInternational Conference on Machine Learning (ICML), 2022 Pier Giuseppe Sessa Maryam Kamgarpour Andreas Krause 167 20 0 14 Mar 2022
Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental LimitsInternational Conference on Machine Learning (ICML), 2022 Qinghua Liu Yuanhao Wang Chi Jin AAML 158 16 0 14 Mar 2022
Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline DatasetsInternational Conference on Machine Learning (ICML), 2022 Han Zhong Wei Xiong Jiyuan Tan Liwei Wang Tong Zhang Zhaoran Wang Zhuoran Yang OffRL 150 41 0 15 Feb 2022
Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic ConvergenceInternational Conference on Machine Learning (ICML), 2022 Dongsheng Ding Chen-Yu Wei Jianchao Tan M. Jovanović 388 76 0 08 Feb 2022
Near-Optimal Learning of Extensive-Form Games with Imperfect InformationInternational Conference on Machine Learning (ICML), 2022 Yunru Bai Chi Jin Song Mei Tiancheng Yu 310 30 0 03 Feb 2022
Cooperative Online Learning in Stochastic and Adversarial MDPsInternational Conference on Machine Learning (ICML), 2022 Tal Lancewicki Aviv A. Rosenberg Yishay Mansour 233 3 0 31 Jan 2022
When is Offline Two-Player Zero-Sum Markov Game Solvable? Qiwen Cui S. Du OffRL 178 29 0 10 Jan 2022
Multi-Agent Reinforcement Learning via Adaptive Kalman Temporal Difference and Successor RepresentationItalian National Conference on Sensors (INS), 2021 Mohammad Salimibeni Arash Mohammadi Parvin Malekzadeh Konstantinos N. Plataniotis 158 6 0 30 Dec 2021
Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers? Han Zhong Zhuoran Yang Zhaoran Wang Sai Li 245 33 0 27 Dec 2021
Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games Zuguang Gao Qianqian Ma Tamer Bacsar J. Birge OffRL 163 9 0 15 Dec 2021
Independent Learning in Stochastic Games Asuman Ozdaglar M. O. Sayin Jianchao Tan 122 32 0 23 Nov 2021
Dueling RL: Reinforcement Learning with Trajectory Preferences Aldo Pacchiano Aadirupa Saha Jonathan Lee 319 102 0 08 Nov 2021
V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL Chi Jin Qinghua Liu Yuanhao Wang Tiancheng Yu OffRL 214 141 0 27 Oct 2021
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game Delin Qu Jieping Ye Zhaoran Wang Zhuoran Yang OffRL 221 25 0 19 Oct 2021
Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation Weitong Zhang Dongruo Zhou Quanquan Gu OffRL 253 31 0 12 Oct 2021
On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement LearningInternational Conference on Machine Learning (ICML), 2021 Weichao Mao Lin F. Yang Jianchao Tan Tamer Bacsar 264 59 0 12 Oct 2021
Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov GamesDynamic Games and Applications (DGA), 2021 Weichao Mao Tamer Basar 227 77 0 12 Oct 2021
Satisficing Paths and Independent Multi-Agent Reinforcement Learning in Stochastic GamesSIAM Journal on Mathematics of Data Science (SIMODS), 2021 Bora Yongacoglu Gürdal Arslan S. Yüksel 207 19 0 09 Oct 2021
When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?International Conference on Learning Representations (ICLR), 2021 Ziang Song Song Mei Yu Bai 196 75 0 08 Oct 2021
A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary OpponentInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Mehdi Jafarnia-Jahromi Rahul Jain A. Nayyar 188 5 0 08 Sep 2021
A Simple Reward-free Approach to Constrained Reinforcement Learning Sobhan Miryoosefi Chi Jin 185 33 0 12 Jul 2021
Online Sub-Sampling for Reinforcement Learning with General Function Approximation Dingwen Kong Ruslan Salakhutdinov Ruosong Wang Lin F. Yang OffRL 187 1 0 14 Jun 2021
Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall Tadashi Kozuno Pierre Ménard Rémi Munos Michal Valko 175 18 0 11 Jun 2021
Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2021 Tengyang Xie Nan Jiang Huan Wang Caiming Xiong Yu Bai OffRL OnRL 252 179 0 09 Jun 2021
The Power of Exploiter: Provable Multi-Agent RL in Large State SpacesInternational Conference on Machine Learning (ICML), 2021 Chi Jin Qinghua Liu Tiancheng Yu 197 55 0 07 Jun 2021
Decentralized Q-Learning in Zero-sum Markov GamesNeural Information Processing Systems (NeurIPS), 2021 M. O. Sayin Jianchao Tan David S. Leslie Tamer Basar Asuman Ozdaglar 163 91 0 04 Jun 2021
Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic SettingsNeural Information Processing Systems (NeurIPS), 2021 Ming Yin Yu Wang OffRL 249 19 0 13 May 2021
Sample-Efficient Learning of Stackelberg Equilibria in General-Sum GamesNeural Information Processing Systems (NeurIPS), 2021 Yu Bai Chi Jin Haiquan Wang Caiming Xiong 240 75 0 23 Feb 2021
Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov GamesInternational Conference on Algorithmic Learning Theory (ALT), 2021 Zixiang Chen Dongruo Zhou Quanquan Gu 146 28 0 15 Feb 2021
Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov GamesAnnual Conference Computational Learning Theory (COLT), 2021 Chen-Yu Wei Chung-Wei Lee Mengxiao Zhang Haipeng Luo 239 87 0 08 Feb 2021
Provably Efficient Algorithms for Multi-Objective Competitive RLInternational Conference on Machine Learning (ICML), 2021 Tiancheng Yu Yi Tian J.N. Zhang S. Sra 189 23 0 05 Feb 2021
Online Learning in Unknown Markov Games Yi Tian Yuanhao Wang Tiancheng Yu S. Sra OffRL 289 13 0 28 Oct 2020
Modular Transfer Learning with Transition Mismatch Compensation for Excessive Disturbance RejectionInternational Journal of Machine Learning and Cybernetics (IJMLC), 2020 Tianming Wang Wenjie Lu H. Yu Dikai Liu 162 1 0 29 Jul 2020
Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample ComplexityNeural Information Processing Systems (NeurIPS), 2020 Jianchao Tan Sham Kakade Tamer Bacsar Lin F. Yang 376 132 0 15 Jul 2020