{"list":"other","total":64,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"1609.07152","title":"Input Convex Neural Networks","created":"2016-09-22","cited_by_count":414},{"id":"1905.05408","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","created":"2019-05-14","cited_by_count":379},{"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":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"2109.09831","title":"SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization","created":"2021-09-20","cited_by_count":230},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"1902.00506","title":"The Hanabi Challenge: A New Frontier for AI Research","created":"2019-02-01","cited_by_count":197},{"id":"2006.10800","title":"Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-06-18","cited_by_count":197},{"id":"1908.09453","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","created":"2019-08-26","cited_by_count":186},{"id":"2006.06224","title":"A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning","created":"2020-06-11","cited_by_count":162},{"id":"1807.02629","title":"Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile","created":"2018-07-07","cited_by_count":136},{"id":"2206.15378","title":"Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning","created":"2022-06-30","cited_by_count":131},{"id":"2005.09814","title":"Mirror Descent Policy Optimization","created":"2020-05-20","cited_by_count":106},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87},{"id":"2007.08714","title":"Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources","created":"2020-07-17","cited_by_count":83},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81},{"id":"1407.5042","title":"Solving Large Imperfect Information Games Using CFR+","created":"2014-07-18","cited_by_count":78},{"id":"1811.01458","title":"Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning","created":"2018-11-04","cited_by_count":68},{"id":"2206.05825","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","created":"2022-06-12","cited_by_count":66},{"id":"1910.01215","title":"ES-MAML: Simple Hessian-Free Meta Learning","created":"2019-09-25","cited_by_count":57},{"id":"2110.14300","title":"Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks","created":"2021-10-27","cited_by_count":54},{"id":"2104.12761","title":"Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibrium","created":"2021-04-26","cited_by_count":51},{"id":"2010.13724","title":"Tight last-iterate convergence rates for no-regret learning in multi-player games","created":"2020-10-26","cited_by_count":49},{"id":"1906.02330","title":"Finding Friend and Foe in Multi-Agent Games","created":"2019-06-05","cited_by_count":42},{"id":"2311.03220","title":"ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents","created":"2023-11-06","cited_by_count":33},{"id":"2203.12056","title":"On Last-Iterate Convergence Beyond Zero-Sum Games","created":"2022-03-22","cited_by_count":31},{"id":"2106.14326","title":"Last-iterate Convergence in Extensive-Form Games","created":"2021-06-27","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":"2109.13851","title":"Reinforcement Learning for Quantitative Trading","created":"2021-09-28","cited_by_count":24},{"id":"2202.11632","title":"Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance","created":"2022-02-23","cited_by_count":24},{"id":"2112.03178","title":"Student of Games: A unified learning algorithm for both perfect and imperfect information games","created":"2021-12-06","cited_by_count":23},{"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":"2106.09435","title":"Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers","created":"2021-06-17","cited_by_count":21},{"id":"2206.09495","title":"The Power of Regularization in Solving Extensive-Form Games","created":"2022-06-19","cited_by_count":21},{"id":"1908.09893","title":"Coarse Correlation in Extensive-Form Games","created":"2019-08-26","cited_by_count":17},{"id":"2210.13417","title":"Avalon: A Benchmark for RL Generalization Using Procedurally Generated Worlds","created":"2022-10-24","cited_by_count":17},{"id":"2101.04237","title":"Solving Common-Payoff Games with Approximate Policy Iteration","created":"2021-01-11","cited_by_count":15},{"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":"2206.04160","title":"Alternating Mirror Descent for Constrained Min-Max Games","created":"2022-06-08","cited_by_count":13},{"id":"1802.04221","title":"Let's be Honest: An Optimal No-Regret Framework for Zero-Sum Games","created":"2018-02-12","cited_by_count":11},{"id":"2202.00082","title":"Trust Region Bounds for Decentralized PPO Under Non-stationarity","created":"2022-01-31","cited_by_count":11},{"id":"2111.00278","title":"A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles","created":"2021-10-30","cited_by_count":9},{"id":"2005.02612","title":"Deep Divergence Learning","created":"2020-05-06","cited_by_count":7},{"id":"2110.04961","title":"Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent","created":"2021-10-11","cited_by_count":7},{"id":"2307.03119","title":"Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance","created":"2023-07-06","cited_by_count":7},{"id":"2203.12074","title":"Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games","created":"2022-03-22","cited_by_count":6},{"id":"2211.01681","title":"Matrix Multiplicative Weights Updates in Quantum Zero-Sum Games: Conservation Laws & Recurrence","created":"2022-11-03","cited_by_count":6},{"id":"2308.16017","title":"Hidden-Role Games: Equilibrium Concepts and Computation","created":"2023-08-30","cited_by_count":6},{"id":"2310.03354","title":"Fictitious Cross-Play: Learning Global Nash Equilibrium in Mixed Cooperative-Competitive Games","created":"2023-10-05","cited_by_count":6},{"id":"2009.08574","title":"Linear Convergence of Generalized Mirror Descent with Time-Dependent Mirrors","created":"2020-09-18","cited_by_count":5},{"id":"2211.08980","title":"Asynchronous Gradient Play in Zero-Sum Multi-agent Games","created":"2022-11-16","cited_by_count":5},{"id":"2303.03196","title":"Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning","created":"2023-03-02","cited_by_count":5},{"id":"2206.04763","title":"Neural Bregman Divergences for Distance Learning","created":"2022-06-09","cited_by_count":3}],"next_cursor":null}