{"total":1558,"rows":[{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395,"area":"agents"},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942,"area":null},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367,"area":"agents"},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237,"area":"agents"},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186,"area":null},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155,"area":null},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142,"area":"offlinerl"},{"id":"2401.03428","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","created":"2024-01-07","cited_by_count":132,"area":"agents"},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"area":null},{"id":"2206.08686","title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","created":"2022-06-17","cited_by_count":119,"area":null},{"id":"2404.02831","title":"Empowering Biomedical Discovery with AI Agents","created":"2024-04-03","cited_by_count":118,"area":null},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114,"area":null},{"id":"2508.03680","title":"Agent Lightning: Train ANY AI Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":109,"area":"lr"},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104,"area":null},{"id":"2310.01320","title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","created":"2023-10-02","cited_by_count":104,"area":"lr"},{"id":"1807.09936","title":"Multi-Agent Generative Adversarial Imitation Learning","created":"2018-07-26","cited_by_count":100,"area":"offlinerl"},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99,"area":null},{"id":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98,"area":null},{"id":"2111.12444","title":"Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications","created":"2021-11-24","cited_by_count":97,"area":null},{"id":"2309.09971","title":"MindAgent: Emergent Gaming Interaction","created":"2023-09-18","cited_by_count":88,"area":null},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2403.12482","title":"Embodied LLM Agents Learn to Cooperate in Organized Teams","created":"2024-03-19","cited_by_count":82,"area":"agents"},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2305.17330","title":"MADiff: Offline Multi-agent Learning with Diffusion Models","created":"2023-05-27","cited_by_count":75,"area":"diffusion"},{"id":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74,"area":null},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70,"area":null},{"id":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2102.03479","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-06","cited_by_count":68,"area":null},{"id":"2205.11814","title":"Penalized Proximal Policy Optimization for Safe Reinforcement Learning","created":"2022-05-24","cited_by_count":68,"area":null},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68,"area":null},{"id":"2310.03903","title":"LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models","created":"2023-10-05","cited_by_count":68,"area":"lr"},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"area":null},{"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,"area":null},{"id":"2405.11106","title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","created":"2024-05-17","cited_by_count":67,"area":"agents"},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"area":null},{"id":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61,"area":null},{"id":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61,"area":"offlinerl"},{"id":"2506.22355","title":"Embodied AI Agents: Modeling the World","created":"2025-06-27","cited_by_count":61,"area":"wm"},{"id":"1907.13220","title":"Multi-Agent Adversarial Inverse Reinforcement Learning","created":"2019-07-30","cited_by_count":60,"area":"offlinerl"},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2111.09189","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","created":"2021-10-15","cited_by_count":58,"area":null},{"id":"2306.09884","title":"Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX","created":"2023-06-16","cited_by_count":58,"area":null},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57,"area":null},{"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,"area":null},{"id":"2102.04402","title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","created":"2021-02-08","cited_by_count":56,"area":null},{"id":"2110.14300","title":"Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks","created":"2021-10-27","cited_by_count":54,"area":null},{"id":"2310.12432","title":"CAT: Closed-loop Adversarial Training for Safe End-to-End Driving","created":"2023-10-19","cited_by_count":54,"area":"driving"},{"id":"2211.03464","title":"A Survey on Quantum Reinforcement Learning","created":"2022-11-07","cited_by_count":53,"area":null},{"id":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50,"area":null},{"id":"2209.10485","title":"Towards a Standardised Performance Evaluation Protocol for Cooperative MARL","created":"2022-09-21","cited_by_count":49,"area":null},{"id":"2404.10775","title":"COMBO: Compositional World Models for Embodied Multi-Agent Cooperation","created":"2024-04-16","cited_by_count":49,"area":"wm"},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48,"area":null},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48,"area":null},{"id":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45,"area":null},{"id":"2307.11620","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","created":"2023-07-21","cited_by_count":43,"area":"offlinerl"},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42,"area":"offlinerl"},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2211.13746","title":"Melting Pot 2.0","created":"2022-11-24","cited_by_count":40,"area":null},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39,"area":null},{"id":"2501.15228","title":"Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning","created":"2025-01-25","cited_by_count":39,"area":"rag"},{"id":"2106.00285","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","created":"2021-06-01","cited_by_count":38,"area":null},{"id":"2311.13884","title":"Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach","created":"2023-11-23","cited_by_count":38,"area":"agents"},{"id":"2110.10614","title":"Independent Natural Policy Gradient Always Converges in Markov Potential Games","created":"2021-10-20","cited_by_count":37,"area":null},{"id":"2110.15349","title":"Learning to Ground Multi-Agent Communication with Autoencoders","created":"2021-10-28","cited_by_count":37,"area":null},{"id":"2302.01605","title":"Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37,"area":"offlinerl"},{"id":"2502.14743","title":"Multi-Agent Coordination across Diverse Applications: A Survey","created":"2025-02-20","cited_by_count":37,"area":"agents"},{"id":"2107.11904","title":"Transferable Dialogue Systems and User Simulators","created":"2021-07-25","cited_by_count":36,"area":null},{"id":"2110.05707","title":"On Improving Model-Free Algorithms for Decentralized Multi-Agent Reinforcement Learning","created":"2021-10-12","cited_by_count":36,"area":null},{"id":"2210.06835","title":"Multi-agent Dynamic Algorithm Configuration","created":"2022-10-13","cited_by_count":36,"area":null},{"id":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36,"area":null},{"id":"2301.07137","title":"Heterogeneous Multi-Robot Reinforcement Learning","created":"2023-01-17","cited_by_count":36,"area":null},{"id":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","cited_by_count":36,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35,"area":null},{"id":"2105.01099","title":"Reinforcement Learning for Ridesharing: An Extended Survey","created":"2021-05-03","cited_by_count":35,"area":null},{"id":"2103.06426","title":"XDO: A Double Oracle Algorithm for Extensive-Form Games","created":"2021-03-11","cited_by_count":34,"area":null},{"id":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34,"area":null},{"id":"2206.10607","title":"MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer","created":"2022-06-20","cited_by_count":34,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2110.13827","title":"Learning to Simulate Self-Driven Particles System with Coordinated Policy Optimization","created":"2021-10-26","cited_by_count":33,"area":null},{"id":"2309.12825","title":"OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control","created":"2023-09-22","cited_by_count":33,"area":null},{"id":"2312.01472","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","created":"2023-12-03","cited_by_count":33,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32,"area":null},{"id":"2206.07505","title":"Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2408.09675","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","created":"2024-08-19","cited_by_count":32,"area":"driving"},{"id":"2102.08159","title":"RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents","created":"2021-02-16","cited_by_count":31,"area":null},{"id":"2412.19726","title":"Position: Theory of Mind Benchmarks are Broken for Large Language Models","created":"2024-12-27","cited_by_count":31,"area":null},{"id":"2105.08692","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","created":"2021-05-18","cited_by_count":30,"area":null},{"id":"2106.10110","title":"Towards Distraction-Robust Active Visual Tracking","created":"2021-06-18","cited_by_count":30,"area":null}],"next_cursor":"100"}