{"list":"other","total":53,"rows":[{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"2012.08630","title":"Open Problems in Cooperative AI","created":"2020-12-15","cited_by_count":168},{"id":"2102.00135","title":"Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes","created":"2021-01-30","cited_by_count":156},{"id":"1906.01786","title":"Global Optimality Guarantees For Policy Gradient Methods","created":"2019-06-05","cited_by_count":150},{"id":"1901.08511","title":"A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach","created":"2019-01-24","cited_by_count":143},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"1807.03907","title":"The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization","created":"2018-07-11","cited_by_count":101},{"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":"2007.12322","title":"Off-Policy Multi-Agent Decomposed Policy Gradients","created":"2020-07-24","cited_by_count":98},{"id":"2106.01969","title":"Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games","created":"2021-06-03","cited_by_count":93},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84},{"id":"2004.13332","title":"The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies","created":"2020-04-28","cited_by_count":75},{"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":"2102.04540","title":"Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games","created":"2021-02-08","cited_by_count":69},{"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":"2105.15186","title":"Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization","created":"2021-05-31","cited_by_count":63},{"id":"2106.02748","title":"Decentralized Q-Learning in Zero-sum Markov Games","created":"2021-06-04","cited_by_count":58},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52},{"id":"2007.11849","title":"Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation","created":"2020-07-23","cited_by_count":48},{"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":"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":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40},{"id":"2110.10614","title":"Independent Natural Policy Gradient Always Converges in Markov Potential Games","created":"2021-10-20","cited_by_count":37},{"id":"2110.05707","title":"On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning","created":"2021-10-12","cited_by_count":36},{"id":"1703.01138","title":"Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos","created":"2017-03-03","cited_by_count":29},{"id":"2103.09284","title":"Learning in Nonzero-Sum Stochastic Games with Potentials","created":"2021-03-16","cited_by_count":26},{"id":"2107.13090","title":"Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games","created":"2021-07-27","cited_by_count":25},{"id":"2103.04972","title":"Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation","created":"2021-03-08","cited_by_count":23},{"id":"2108.02904","title":"Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist","created":"2021-08-06","cited_by_count":23},{"id":"2111.11743","title":"Independent Learning in Stochastic Games","created":"2021-11-23","cited_by_count":22},{"id":"1802.00899","title":"Learning Parametric Closed-Loop Policies for Markov Potential Games","created":"2018-02-03","cited_by_count":21},{"id":"2106.12928","title":"Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality","created":"2021-06-24","cited_by_count":21},{"id":"1803.05028","title":"Decentralised Learning in Systems with Many, Many Strategic Agents","created":"2018-03-13","cited_by_count":20},{"id":"1907.03712","title":"Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games","created":"2019-07-08","cited_by_count":17},{"id":"2012.03083","title":"Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory","created":"2020-12-05","cited_by_count":17},{"id":"1911.04672","title":"Global Convergence of Policy Gradient for Sequential Zero-Sum Linear Quadratic Dynamic Games","created":"2019-11-12","cited_by_count":16},{"id":"2005.13996","title":"Chaos, Extremism and Optimism: Volume Analysis of Learning in Games","created":"2020-05-28","cited_by_count":16},{"id":"1905.04532","title":"Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes","created":"2019-05-11","cited_by_count":14},{"id":"2111.00781","title":"Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure","created":"2021-11-01","cited_by_count":14},{"id":"1606.03000","title":"On Projected Stochastic Gradient Descent Algorithm with Weighted Averaging for Least Squares Regression","created":"2016-06-09","cited_by_count":9},{"id":"2008.00540","title":"Chaos of Learning Beyond Zero-sum and Coordination via Game Decompositions","created":"2020-08-02","cited_by_count":9},{"id":"1509.01313","title":"Dynamic Potential Games in Communications: Fundamentals and Applications","created":"2015-09-04","cited_by_count":8},{"id":"2111.13872","title":"Normative Disagreement as a Challenge for Cooperative AI","created":"2021-11-27","cited_by_count":7}],"next_cursor":null}