{"list":"other","total":51,"rows":[{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223},{"id":"2112.13487","title":"The Statistical Complexity of Interactive Decision Making","created":"2021-12-27","cited_by_count":218},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178},{"id":"1908.00261","title":"On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift","created":"2019-08-01","cited_by_count":177},{"id":"1910.03016","title":"Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?","created":"2019-10-07","cited_by_count":140},{"id":"1506.03271","title":"Explore no more: Improved high-probability regret bounds for non-stochastic bandits","created":"2015-06-10","cited_by_count":120},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114},{"id":"2002.04017","title":"Provable Self-Play Algorithms for Competitive Reinforcement Learning","created":"2020-02-10","cited_by_count":113},{"id":"2006.12007","title":"Near-Optimal Reinforcement Learning with Self-Play","created":"2020-06-22","cited_by_count":109},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"2101.04233","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","created":"2021-01-11","cited_by_count":101},{"id":"2002.07066","title":"Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium","created":"2020-02-17","cited_by_count":100},{"id":"2106.01969","title":"Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games","created":"2021-06-03","cited_by_count":93},{"id":"2007.07461","title":"Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity","created":"2020-07-15","cited_by_count":92},{"id":"2007.08459","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","created":"2020-07-16","cited_by_count":92},{"id":"1811.03056","title":"Policy Certificates: Towards Accountable Reinforcement Learning","created":"2018-11-07","cited_by_count":81},{"id":"2010.01374","title":"Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions","created":"2020-10-03","cited_by_count":71},{"id":"2110.04184","title":"When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?","created":"2021-10-08","cited_by_count":67},{"id":"2106.02748","title":"Decentralized Q-Learning in Zero-sum Markov Games","created":"2021-06-04","cited_by_count":58},{"id":"2202.04129","title":"Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence","created":"2022-02-08","cited_by_count":57},{"id":"2205.15512","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","created":"2022-05-31","cited_by_count":55},{"id":"2204.03991","title":"The Complexity of Markov Equilibrium in Stochastic Games","created":"2022-04-08","cited_by_count":49},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48},{"id":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44},{"id":"2002.00287","title":"Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits","created":"2020-02-01","cited_by_count":43},{"id":"2107.14702","title":"Towards General Function Approximation in Zero-Sum Markov Games","created":"2021-07-30","cited_by_count":43},{"id":"2001.11568","title":"Faster Projection-free Online Learning","created":"2020-01-30","cited_by_count":40},{"id":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40},{"id":"2110.05707","title":"On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning","created":"2021-10-12","cited_by_count":36},{"id":"2106.00198","title":"Gradient play in stochastic games: stationary points, convergence, and sample complexity","created":"2021-06-01","cited_by_count":34},{"id":"2206.00159","title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus","created":"2022-06-01","cited_by_count":30},{"id":"2201.03522","title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","created":"2022-01-10","cited_by_count":28},{"id":"2210.01050","title":"Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games","created":"2022-10-03","cited_by_count":26},{"id":"2207.14211","title":"Regret Minimization and Convergence to Equilibria in General-sum Markov Games","created":"2022-07-28","cited_by_count":24},{"id":"1307.4847","title":"Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization","created":"2013-07-18","cited_by_count":19},{"id":"2206.02640","title":"Policy Optimization for Markov Games: Unified Framework and Faster Convergence","created":"2022-06-06","cited_by_count":16},{"id":"2210.16976","title":"Representation Learning for General-sum Low-rank Markov Games","created":"2022-10-30","cited_by_count":15},{"id":"2209.12430","title":"$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games","created":"2022-09-26","cited_by_count":11},{"id":"2206.01880","title":"Learning in Congestion Games with Bandit Feedback","created":"2022-06-04","cited_by_count":10},{"id":"2206.00796","title":"Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning","created":"2022-06-01","cited_by_count":5}],"next_cursor":null}