{"total":137,"rows":[{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"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":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98,"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":"2102.04402","title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","created":"2021-02-08","cited_by_count":56,"area":null},{"id":"2509.25541","title":"Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play","created":"2025-09-29","cited_by_count":37,"area":"mllm"},{"id":"2301.07137","title":"Heterogeneous Multi-Robot Reinforcement Learning","created":"2023-01-17","cited_by_count":36,"area":null},{"id":"2309.05655","title":"Dynamic Handover: Throw and Catch with Bimanual Hands","created":"2023-09-11","cited_by_count":35,"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":"2105.08692","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","created":"2021-05-18","cited_by_count":30,"area":null},{"id":"2102.07936","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2404.10976","title":"Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning","created":"2024-04-17","cited_by_count":18,"area":null},{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16,"area":null},{"id":"2112.03547","title":"Self-Organized Polynomial-Time Coordination Graphs","created":"2021-12-07","cited_by_count":15,"area":null},{"id":"2205.02561","title":"LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning","created":"2022-05-05","cited_by_count":15,"area":null},{"id":"2203.04482","title":"Multi-Agent Policy Transfer via Task Relationship Modeling","created":"2022-03-09","cited_by_count":14,"area":null},{"id":"2305.02128","title":"System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning","created":"2023-05-03","cited_by_count":14,"area":null},{"id":"2406.07428","title":"GemNet: Menu-Based, Strategy-Proof Multi-Bidder Auctions Through Deep Learning","created":"2024-06-11","cited_by_count":14,"area":null},{"id":"2106.00517","title":"Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment","created":"2021-06-01","cited_by_count":12,"area":null},{"id":"2107.07506","title":"Adaptable Agent Populations via a Generative Model of Policies","created":"2021-07-15","cited_by_count":12,"area":null},{"id":"2304.00755","title":"Effective and Stable Role-Based Multi-Agent Collaboration by Structural Information Principles","created":"2023-04-03","cited_by_count":12,"area":null},{"id":"2207.05683","title":"Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL","created":"2022-06-01","cited_by_count":11,"area":null},{"id":"2405.15054","title":"Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2412.04233","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","created":"2024-12-05","cited_by_count":11,"area":null},{"id":"2211.08404","title":"Non-Linear Coordination Graphs","created":"2022-10-26","cited_by_count":10,"area":null},{"id":"2407.12532","title":"Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models","created":"2024-07-17","cited_by_count":10,"area":"lr"},{"id":"2408.14597","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","created":"2024-08-26","cited_by_count":10,"area":null},{"id":"2109.12508","title":"LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates","created":"2021-09-26","cited_by_count":9,"area":null},{"id":"2308.11272","title":"FoX: Formation-aware exploration in multi-agent reinforcement learning","created":"2023-08-22","cited_by_count":9,"area":null},{"id":"2402.04971","title":"Multi-Sender Persuasion: A Computational Perspective","created":"2024-02-07","cited_by_count":9,"area":null},{"id":"2412.07880","title":"Towards Foundation-model-based Multiagent System to Accelerate AI for Social Impact","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2205.09362","title":"Sparse Adversarial Attack in Multi-agent Reinforcement Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2206.02583","title":"Consensus Learning for Cooperative Multi-Agent Reinforcement Learning","created":"2022-06-06","cited_by_count":8,"area":null},{"id":"2207.03902","title":"Interaction Pattern Disentangling for Multi-Agent Reinforcement Learning","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2305.10865","title":"Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning","created":"2023-05-18","cited_by_count":8,"area":"agents"},{"id":"2508.12683","title":"A Taxonomy of Hierarchical Multi-Agent Systems: Design Patterns, Coordination Mechanisms, and Industrial Applications","created":"2025-08-18","cited_by_count":8,"area":"agents"},{"id":"2105.06228","title":"SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning","created":"2021-05-13","cited_by_count":7,"area":null},{"id":"2403.19253","title":"Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning","created":"2024-03-28","cited_by_count":7,"area":null},{"id":"2108.12988","title":"Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning","created":"2021-08-30","cited_by_count":6,"area":null},{"id":"2204.09418","title":"Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2404.03869","title":"Heterogeneous Multi-Agent Reinforcement Learning for Zero-Shot Scalable Collaboration","created":"2024-04-05","cited_by_count":6,"area":null},{"id":"2405.16386","title":"Variational Offline Multi-agent Skill Discovery","created":"2024-05-26","cited_by_count":6,"area":null},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2410.08540","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2110.07392","title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2204.12937","title":"Learning to Transfer Role Assignment Across Team Sizes","created":"2022-04-17","cited_by_count":5,"area":null},{"id":"2212.07684","title":"Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2304.07520","title":"STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2410.13953","title":"On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow","created":"2024-10-17","cited_by_count":5,"area":"diffusion"},{"id":"2502.04773","title":"An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2503.15703","title":"Predicting Multi-Agent Specialization via Task Parallelizability","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2604.17745","title":"HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution","created":"2026-04-20","cited_by_count":5,"area":"agents"},{"id":"2401.11257","title":"Measuring Policy Distance for Multi-Agent Reinforcement Learning","created":"2024-01-20","cited_by_count":4,"area":null},{"id":"2412.15517","title":"Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning","created":"2024-12-20","cited_by_count":4,"area":null},{"id":"2412.16244","title":"The impact of behavioral diversity in multi-agent reinforcement learning","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2505.17734","title":"URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles","created":"2025-05-23","cited_by_count":4,"area":"driving"},{"id":"2509.16606","title":"Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2511.12754","title":"Adaptively Coordinating with Novel Partners via Learned Latent Strategies","created":"2025-11-16","cited_by_count":4,"area":null},{"id":"2106.05907","title":"DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation","created":"2021-06-10","cited_by_count":3,"area":null},{"id":"2110.03032","title":"Learning Multi-Objective Curricula for Robotic Policy Learning","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2110.08642","title":"Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning","created":"2021-10-16","cited_by_count":3,"area":null},{"id":"2112.06771","title":"Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution","created":"2021-12-09","cited_by_count":3,"area":null},{"id":"2206.11054","title":"S2RL: Do We Really Need to Perceive All States in Deep Multi-Agent Reinforcement Learning?","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2302.04944","title":"Learning Complex Teamwork Tasks Using a Given Sub-task Decomposition","created":"2023-02-09","cited_by_count":3,"area":null},{"id":"2302.05593","title":"ReMIX: Regret Minimization for Monotonic Value Function Factorization in Multiagent Reinforcement Learning","created":"2023-02-11","cited_by_count":3,"area":null},{"id":"2309.04615","title":"VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Model","created":"2023-09-08","cited_by_count":3,"area":"wm"},{"id":"2405.16854","title":"Knowing What Not to Do: Leverage Language Model Insights for Action Space Pruning in Multi-agent Reinforcement Learning","created":"2024-05-27","cited_by_count":3,"area":"agents"},{"id":"2508.18708","title":"Skill-Aligned Fairness in Multi-Agent Learning for Collaboration in Healthcare","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2510.17697","title":"A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2512.01610","title":"Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs","created":"2025-12-01","cited_by_count":3,"area":"agents"},{"id":"2602.17062","title":"Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2102.12957","title":"Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2210.13942","title":"Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2211.14426","title":"A Critical Review of Traffic Signal Control and A Novel Unified View of Reinforcement Learning and Model Predictive Control Approaches for Adaptive Traffic Signal Control","created":"2022-11-26","cited_by_count":2,"area":null},{"id":"2301.13812","title":"Learning Roles with Emergent Social Value Orientations","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2304.00977","title":"Selective Reincarnation: Offline-to-Online Multi-Agent Reinforcement Learning","created":"2023-03-31","cited_by_count":2,"area":"offlinerl"},{"id":"2312.08468","title":"On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2402.14090","title":"Social Environment Design","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2501.15695","title":"Contextual Knowledge Sharing in Multi-Agent Reinforcement Learning with Decentralized Communication and Coordination","created":"2025-01-26","cited_by_count":2,"area":null},{"id":"2503.01440","title":"Trajectory-Class-Aware Multi-Agent Reinforcement Learning","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2506.09434","title":"When Is Diversity Rewarded in Cooperative Multi-Agent Learning?","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2509.12927","title":"HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making","created":"2025-09-16","cited_by_count":2,"area":"agents"},{"id":"2603.08399","title":"A Recipe for Stable Offline Multi-agent Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"offlinerl"},{"id":"2102.04775","title":"Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2110.08169","title":"Containerized Distributed Value-Based Multi-Agent Reinforcement Learning","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2206.09590","title":"From Multi-agent to Multi-robot: A Scalable Training and Evaluation Platform for Multi-robot Reinforcement Learning","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2212.07397","title":"Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2304.00009","title":"The challenge of redundancy on multi-agent value factorisation","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2304.05632","title":"Multi-agent Policy Reciprocity with Theoretical Guarantee","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2305.07182","title":"Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning","created":"2023-05-12","cited_by_count":1,"area":null},{"id":"2306.02430","title":"A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning","created":"2023-06-04","cited_by_count":1,"area":null},{"id":"2308.09909","title":"Never Explore Repeatedly in Multi-Agent Reinforcement Learning","created":"2023-08-19","cited_by_count":1,"area":null},{"id":"2403.01816","title":"SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2403.18056","title":"Self-Clustering Hierarchical Multi-Agent Reinforcement Learning with Extensible Cooperation Graph","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2407.00741","title":"Diffusion Models for Offline Multi-agent Reinforcement Learning with Safety Constraints","created":"2024-06-30","cited_by_count":1,"area":"diffusion"},{"id":"2409.11741","title":"HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning","created":"2024-09-18","cited_by_count":1,"area":null},{"id":"2501.02221","title":"CORD: Generalizable Cooperation via Role Diversity","created":"2025-01-04","cited_by_count":1,"area":"deeprl"},{"id":"2501.10367","title":"GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2507.18867","title":"Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise","created":"2025-07-25","cited_by_count":1,"area":null}],"next_cursor":"100"}