{"list":"other","total":68,"rows":[{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"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":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"2007.06700","title":"Revisiting Fundamentals of Experience Replay","created":"2020-07-13","cited_by_count":175},{"id":"2104.02151","title":"Distributed Learning in Wireless Networks: Recent Progress and Future Challenges","created":"2021-04-05","cited_by_count":129},{"id":"1712.01275","title":"A Deeper Look at Experience Replay","created":"2017-12-04","cited_by_count":105},{"id":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73},{"id":"1712.00600","title":"MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence","created":"2017-12-02","cited_by_count":71},{"id":"2007.14430","title":"Munchausen Reinforcement Learning","created":"2020-07-28","cited_by_count":69},{"id":"1804.03980","title":"Emergent Communication through Negotiation","created":"2018-04-11","cited_by_count":62},{"id":"2007.03458","title":"Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications","created":"2020-07-05","cited_by_count":62},{"id":"2205.12944","title":"Learning in Mean Field Games: A Survey","created":"2022-05-25","cited_by_count":61},{"id":"1910.12802","title":"Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning","created":"2019-10-28","cited_by_count":59},{"id":"2010.00145","title":"Entropy Regularization for Mean Field Games with Learning","created":"2020-09-30","cited_by_count":58},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56},{"id":"2002.02325","title":"Social diversity and social preferences in mixed-motive reinforcement learning","created":"2020-02-06","cited_by_count":49},{"id":"2006.13912","title":"Unified Reinforcement Q-Learning for Mean Field Game and Control Problems","created":"2020-06-24","cited_by_count":49},{"id":"1907.02633","title":"On the Convergence of Model Free Learning in Mean Field Games","created":"2019-07-04","cited_by_count":48},{"id":"2006.08555","title":"Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games","created":"2020-06-15","cited_by_count":47},{"id":"2003.12151","title":"Q-Learning in Regularized Mean-field Games","created":"2020-03-24","cited_by_count":42},{"id":"1806.00877","title":"Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization","created":"2018-06-03","cited_by_count":40},{"id":"1507.06280","title":"Learning in Mean Field Games: the Fictitious Play","created":"2015-07-22","cited_by_count":38},{"id":"2203.11973","title":"Scalable Deep Reinforcement Learning Algorithms for Mean Field Games","created":"2022-03-22","cited_by_count":38},{"id":"2103.00623","title":"Scaling up Mean Field Games with Online Mirror Descent","created":"2021-02-28","cited_by_count":32},{"id":"1612.07878","title":"Markov-Nash Equilibria in Mean-Field Games with Discounted Cost","created":"2016-12-23","cited_by_count":31},{"id":"2105.07933","title":"Mean Field Games Flock! The Reinforcement Learning Way","created":"2021-05-17","cited_by_count":31},{"id":"2109.09717","title":"Generalization in Mean Field Games by Learning Master Policies","created":"2021-09-20","cited_by_count":28},{"id":"2002.02513","title":"Multi Type Mean Field Reinforcement Learning","created":"2020-02-06","cited_by_count":26},{"id":"2212.14449","title":"Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games","created":"2022-12-29","cited_by_count":26},{"id":"1905.00358","title":"Deep Learning Methods for Mean Field Control Problems with Delay","created":"2019-05-01","cited_by_count":25},{"id":"2003.06069","title":"A General Framework for Learning Mean-Field Games","created":"2020-03-13","cited_by_count":25},{"id":"1912.03821","title":"Decentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent Advances","created":"2019-12-09","cited_by_count":23},{"id":"2011.08434","title":"Simple and optimal methods for stochastic variational inequalities, II: Markovian noise and policy evaluation in reinforcement learning","created":"2020-11-15","cited_by_count":23},{"id":"2003.04444","title":"Mean Field Games and Applications: Numerical Aspects","created":"2020-03-09","cited_by_count":22},{"id":"2106.06231","title":"Numerical Methods for Mean Field Games and Mean Field Type Control","created":"2021-06-11","cited_by_count":22},{"id":"1903.06372","title":"A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning","created":"2019-03-15","cited_by_count":21},{"id":"2006.11917","title":"Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration for Mean-Field Reinforcement Learning","created":"2020-06-21","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":"2107.04568","title":"Deep Learning for Mean Field Games and Mean Field Control with Applications to Finance","created":"2021-07-09","cited_by_count":20},{"id":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20},{"id":"1909.12678","title":"Numerical resolution of McKean-Vlasov FBSDEs using neural networks","created":"2019-09-27","cited_by_count":19},{"id":"1910.07498","title":"Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games","created":"2019-10-16","cited_by_count":19},{"id":"1907.03053","title":"A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning","created":"2019-07-06","cited_by_count":16},{"id":"2003.04108","title":"Stable Policy Optimization via Off-Policy Divergence Regularization","created":"2020-03-09","cited_by_count":16},{"id":"2012.15791","title":"Partially Observable Mean Field Reinforcement Learning","created":"2020-12-31","cited_by_count":16},{"id":"2110.00304","title":"Divergence-Regularized Multi-Agent Actor-Critic","created":"2021-10-01","cited_by_count":15},{"id":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14},{"id":"2305.11283","title":"On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation","created":"2023-05-18","cited_by_count":14},{"id":"2112.09099","title":"Decentralized Mean Field Games","created":"2021-12-16","cited_by_count":12},{"id":"1608.07701","title":"Proximal methods for stationary Mean Field Games with local couplings","created":"2016-08-27","cited_by_count":11},{"id":"1905.04152","title":"Massive Autonomous UAV Path Planning: A Neural Network Based Mean-Field Game Theoretic Approach","created":"2019-05-10","cited_by_count":10},{"id":"1903.06053","title":"A Game-Theoretic Framework for Autonomous Vehicles Velocity Control: Bridging Microscopic Differential Games and Macroscopic Mean Field Games","created":"2019-03-14","cited_by_count":9},{"id":"2004.02073","title":"Model-free Reinforcement Learning for Non-stationary Mean Field Games","created":"2020-04-05","cited_by_count":7},{"id":"2209.12772","title":"Generalized conditional gradient and learning in potential mean field games","created":"2022-09-26","cited_by_count":5},{"id":"2304.01547","title":"Regularization of the policy updates for stabilizing Mean Field Games","created":"2023-04-04","cited_by_count":5},{"id":"1701.00196","title":"Robust Mean Field Linear-Quadratic-Gaussian Games with Unknown $L^2$-Disturbance","created":"2017-01-01","cited_by_count":4},{"id":"1304.3393","title":"Generic Behaviour Similarity Measures for Evolutionary Swarm Robotics","created":"2013-04-11","cited_by_count":3},{"id":"1811.07799","title":"Distributed Learning of Average Belief Over Networks Using Sequential Observations","created":"2018-11-19","cited_by_count":3},{"id":"1410.4421","title":"Decentralized Convergence to Nash Equilibria in Constrained Deterministic Mean Field Control","created":"2014-10-16","cited_by_count":2},{"id":"1912.01952","title":"A Mean Field Games Model for Cryptocurrency Mining","created":"2019-12-04","cited_by_count":2},{"id":"1506.07719","title":"Network Aggregative Games and Distributed Mean Field Control via Consensus Theory","created":"2015-06-25","cited_by_count":1},{"id":"2001.03232","title":"Optimal dynamic information provision in traffic routing","created":"2020-01-09","cited_by_count":1},{"id":"2103.07714","title":"Mean Field Behaviour of Collaborative Multi-Agent Foragers","created":"2021-03-13","cited_by_count":1},{"id":"2111.06426","title":"A Robust Mean-field Game of Boltzmann-Vlasov-like Traffic Flow","created":"2021-11-11","cited_by_count":1}],"next_cursor":null}