{"list":"other","total":52,"rows":[{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"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":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"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":"1402.0555","title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","created":"2014-02-04","cited_by_count":201},{"id":"2012.08507","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2020-12-15","cited_by_count":200},{"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":"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":"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":"1712.00579","title":"Online Reinforcement Learning in Stochastic Games","created":"2017-12-02","cited_by_count":67},{"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":"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":"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":"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":"1906.00729","title":"Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games","created":"2019-05-31","cited_by_count":42},{"id":"1908.11071","title":"Solving Discounted Stochastic Two-Player Games with Near-Optimal Time and Sample Complexity","created":"2019-08-29","cited_by_count":42},{"id":"2110.05682","title":"Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games","created":"2021-10-12","cited_by_count":42},{"id":"2001.11568","title":"Faster Projection-free Online Learning","created":"2020-01-30","cited_by_count":40},{"id":"2102.11494","title":"Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games","created":"2021-02-23","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":"1606.04550","title":"Settling the complexity of computing approximate two-player Nash equilibria","created":"2016-06-14","cited_by_count":31},{"id":"2206.00159","title":"Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus","created":"2022-06-01","cited_by_count":30},{"id":"2302.03673","title":"Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation","created":"2023-02-07","cited_by_count":27},{"id":"2202.01752","title":"Near-Optimal Learning of Extensive-Form Games with Imperfect Information","created":"2022-02-03","cited_by_count":26},{"id":"2102.07404","title":"Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games","created":"2021-02-15","cited_by_count":25},{"id":"1906.00423","title":"Feature-Based Q-Learning for Two-Player Stochastic Games","created":"2019-06-02","cited_by_count":24},{"id":"2106.06279","title":"Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall","created":"2021-06-11","cited_by_count":21},{"id":"2203.06803","title":"Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits","created":"2022-03-14","cited_by_count":17},{"id":"2206.02640","title":"Policy Optimization for Markov Games: Unified Framework and Faster Convergence","created":"2022-06-06","cited_by_count":16},{"id":"2210.01907","title":"A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games","created":"2022-10-04","cited_by_count":16},{"id":"2205.15294","title":"Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent","created":"2022-05-30","cited_by_count":15},{"id":"2210.16976","title":"Representation Learning for General-sum Low-rank Markov Games","created":"2022-10-30","cited_by_count":15},{"id":"2206.01588","title":"Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games","created":"2022-06-03","cited_by_count":12},{"id":"2212.12567","title":"Adapting to game trees in zero-sum imperfect information games","created":"2022-12-23","cited_by_count":11},{"id":"2205.07223","title":"Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games","created":"2022-05-15","cited_by_count":7},{"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}