{"list":"other","total":107,"rows":[{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"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":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"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":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"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":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"2405.10369","title":"Reinforcement learning","created":"2024-05-16","cited_by_count":247},{"id":"2006.07869","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","created":"2020-06-14","cited_by_count":212},{"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":"1906.08291","title":"Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks","created":"2019-06-19","cited_by_count":199},{"id":"2003.02979","title":"\"Other-Play\" for Zero-Shot Coordination","created":"2020-03-06","cited_by_count":198},{"id":"1902.00506","title":"The Hanabi Challenge: A New Frontier for AI Research","created":"2019-02-01","cited_by_count":197},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"2503.01935","title":"MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents","created":"2025-03-03","cited_by_count":178},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"2010.01523","title":"RODE: Learning Roles to Decompose Multi-Agent Tasks","created":"2020-10-04","cited_by_count":125},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122},{"id":"2010.09776","title":"SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving","created":"2020-10-19","cited_by_count":121},{"id":"2206.08686","title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","created":"2022-06-17","cited_by_count":119},{"id":"1905.05217","title":"CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario","created":"2019-05-13","cited_by_count":115},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104},{"id":"1707.09183","title":"A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity","created":"2017-07-28","cited_by_count":94},{"id":"1910.05366","title":"Learning Nearly Decomposable Value Functions Via Communication Minimization","created":"2019-10-11","cited_by_count":86},{"id":"2106.03400","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","created":"2021-06-07","cited_by_count":79},{"id":"1907.05707","title":"Shapley Q-value: A Local Reward Approach to Solve Global Reward Games","created":"2019-07-11","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":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69},{"id":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61},{"id":"2011.03615","title":"Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial","created":"2020-11-06","cited_by_count":60},{"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":"2311.08562","title":"MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration","created":"2023-11-14","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":"2003.10423","title":"Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning","created":"2020-03-23","cited_by_count":48},{"id":"2310.08901","title":"Welfare Diplomacy: Benchmarking Language Model Cooperation","created":"2023-10-13","cited_by_count":45},{"id":"2307.11620","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","created":"2023-07-21","cited_by_count":43},{"id":"2502.20073","title":"Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents","created":"2025-02-27","cited_by_count":41},{"id":"2312.01058","title":"A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment","created":"2023-12-02","cited_by_count":39},{"id":"2006.04222","title":"Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning","created":"2020-06-07","cited_by_count":38},{"id":"2107.04050","title":"Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning","created":"2021-07-08","cited_by_count":38},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37},{"id":"1909.02790","title":"From Few to More: Large-scale Dynamic Multiagent Curriculum Learning","created":"2019-09-06","cited_by_count":36},{"id":"2210.06835","title":"Multi-agent Dynamic Algorithm Configuration","created":"2022-10-13","cited_by_count":36},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36},{"id":"2406.05720","title":"VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft","created":"2024-06-09","cited_by_count":35},{"id":"2006.06555","title":"Multi-Agent Reinforcement Learning in Stochastic Networked Systems","created":"2020-06-11","cited_by_count":32},{"id":"2012.05893","title":"Flatland-RL : Multi-Agent Reinforcement Learning on Trains","created":"2020-12-10","cited_by_count":32},{"id":"2109.04024","title":"On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)","created":"2021-09-09","cited_by_count":32},{"id":"1809.07124","title":"Pommerman: A Multi-Agent Playground","created":"2018-09-19","cited_by_count":30},{"id":"2302.04831","title":"Cooperative Open-ended Learning Framework for Zero-shot Coordination","created":"2023-02-09","cited_by_count":30},{"id":"2106.02886","title":"Context-Aware Sparse Deep Coordination Graphs","created":"2021-06-05","cited_by_count":28},{"id":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","cited_by_count":28},{"id":"2002.02513","title":"Multi Type Mean Field Reinforcement Learning","created":"2020-02-06","cited_by_count":26},{"id":"2105.15013","title":"SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning","created":"2021-05-31","cited_by_count":26},{"id":"2111.04613","title":"Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems","created":"2021-11-08","cited_by_count":26},{"id":"2408.15971","title":"BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems","created":"2024-08-28","cited_by_count":26},{"id":"2205.15023","title":"Scalable Multi-Agent Model-Based Reinforcement Learning","created":"2022-05-25","cited_by_count":25},{"id":"2105.03363","title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","created":"2021-05-07","cited_by_count":24},{"id":"2201.12436","title":"Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination","created":"2022-01-28","cited_by_count":23},{"id":"2108.01843","title":"Model-Based Opponent Modeling","created":"2021-08-04","cited_by_count":22},{"id":"2002.04235","title":"Learning Structured Communication for Multi-agent Reinforcement Learning","created":"2020-02-11","cited_by_count":21},{"id":"1910.12639","title":"MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding","created":"2019-10-25","cited_by_count":20},{"id":"2306.10715","title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","created":"2023-06-19","cited_by_count":19},{"id":"2501.08328","title":"PokerBench: Training Large Language Models to become Professional Poker Players","created":"2025-01-14","cited_by_count":18},{"id":"2012.15791","title":"Partially Observable Mean Field Reinforcement Learning","created":"2020-12-31","cited_by_count":16},{"id":"2103.03662","title":"MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models","created":"2021-03-05","cited_by_count":16},{"id":"2305.17568","title":"Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities","created":"2023-05-27","cited_by_count":15},{"id":"2203.04482","title":"Multi-Agent Policy Transfer via Task Relationship Modeling","created":"2022-03-09","cited_by_count":14},{"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":"2107.06434","title":"Centralized Model and Exploration Policy for Multi-Agent RL","created":"2021-07-14","cited_by_count":12},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12},{"id":"2305.13937","title":"Multi-agent Continual Coordination via Progressive Task Contextualization","created":"2023-05-07","cited_by_count":11},{"id":"2506.14990","title":"MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning","created":"2025-06-17","cited_by_count":11},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10},{"id":"2311.03736","title":"Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning","created":"2023-11-07","cited_by_count":9},{"id":"2408.07841","title":"SustainDC: Benchmarking for Sustainable Data Center Control","created":"2024-08-14","cited_by_count":8},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8},{"id":"2203.06416","title":"Concentration Network for Reinforcement Learning of Large-Scale Multi-Agent Systems","created":"2022-03-12","cited_by_count":7},{"id":"2501.13592","title":"WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control","created":"2025-01-23","cited_by_count":7}],"next_cursor":"100"}