{"total":126,"rows":[{"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":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"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":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68,"area":null},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"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":"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":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45,"area":null},{"id":"2110.02793","title":"Multi-Agent Constrained Policy Optimisation","created":"2021-10-06","cited_by_count":35,"area":null},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2210.13708","title":"MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library","created":"2022-10-11","cited_by_count":21,"area":null},{"id":"2407.14931","title":"POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding","created":"2024-07-20","cited_by_count":21,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2302.03322","title":"Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2107.01460","title":"Mava: a research library for distributed multi-agent reinforcement learning in JAX","created":"2021-07-03","cited_by_count":16,"area":null},{"id":"2210.15479","title":"Low-Rank Modular Reinforcement Learning via Muscle Synergy","created":"2022-10-26","cited_by_count":16,"area":null},{"id":"2110.00304","title":"Divergence-Regularized Multi-Agent Actor-Critic","created":"2021-10-01","cited_by_count":15,"area":null},{"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,"area":null},{"id":"2210.17375","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","created":"2022-10-26","cited_by_count":14,"area":null},{"id":"2406.02081","title":"FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12,"area":null},{"id":"2312.15908","title":"Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding","created":"2023-12-26","cited_by_count":12,"area":null},{"id":"2412.04233","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","created":"2024-12-05","cited_by_count":11,"area":null},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2408.14597","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","created":"2024-08-26","cited_by_count":10,"area":null},{"id":"2410.01706","title":"Sable: a Performant, Efficient and Scalable Sequence Model for MARL","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2306.11551","title":"IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL","created":"2023-06-20","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":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"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":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2506.00439","title":"RLAE: Reinforcement Learning-Assisted Ensemble for LLMs","created":"2025-05-31","cited_by_count":7,"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":"2410.08540","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2502.04028","title":"Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2504.15425","title":"Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL","created":"2025-04-21","cited_by_count":6,"area":null},{"id":"2202.09422","title":"Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games","created":"2022-02-18","cited_by_count":5,"area":null},{"id":"2209.08244","title":"MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning","created":"2022-09-17","cited_by_count":5,"area":null},{"id":"2211.03032","title":"Decentralized Policy Optimization","created":"2022-11-06","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":"2304.10351","title":"Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2305.10091","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2305.18875","title":"Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2401.04934","title":"Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2401.08728","title":"AgentMixer: Multi-Agent Correlated Policy Factorization","created":"2024-01-16","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":"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":"2302.01188","title":"Best Possible Q-Learning","created":"2023-02-02","cited_by_count":4,"area":null},{"id":"2305.19891","title":"Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2306.17411","title":"Decentralized Motor Skill Learning for Complex Robotic Systems","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2311.01953","title":"Optimistic Multi-Agent Policy Gradient","created":"2023-11-03","cited_by_count":4,"area":null},{"id":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","cited_by_count":4,"area":null},{"id":"2204.12064","title":"PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications","created":"2022-04-26","cited_by_count":3,"area":null},{"id":"2210.05367","title":"Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2408.06920","title":"Multi-Agent Continuous Control with Generative Flow Networks","created":"2024-08-13","cited_by_count":3,"area":null},{"id":"2507.18059","title":"Multi-Agent Guided Policy Optimization","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2508.06836","title":"Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning","created":"2025-08-09","cited_by_count":3,"area":null},{"id":"2509.10656","title":"Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration","created":"2025-09-12","cited_by_count":3,"area":null},{"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":"2203.13319","title":"Remember and Forget Experience Replay for Multi-Agent Reinforcement Learning","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2206.11420","title":"PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning","created":"2022-06-22","cited_by_count":2,"area":null},{"id":"2302.08139","title":"Model-Based Decentralized Policy Optimization","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2312.14292","title":"Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2402.14090","title":"Social Environment Design","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2403.06397","title":"DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2509.09135","title":"Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2602.20804","title":"Probing Dec-POMDP Reasoning in Cooperative MARL","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2606.18308","title":"TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2111.05670","title":"DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2202.03558","title":"Attacking c-MARL More Effectively: A Data Driven Approach","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2203.07562","title":"Safe adaptation in multiagent competition","created":"2022-03-14","cited_by_count":1,"area":null},{"id":"2209.01054","title":"Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction","created":"2022-09-02","cited_by_count":1,"area":null},{"id":"2211.11886","title":"Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition","created":"2022-11-21","cited_by_count":1,"area":null},{"id":"2212.02733","title":"CURO: Curriculum Learning for Relative Overgeneralization","created":"2022-12-06","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":"2302.02180","title":"Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative Multi-Agent Reinforcement Learning","created":"2023-02-04","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":"2312.15667","title":"TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient","created":"2023-12-25","cited_by_count":1,"area":null},{"id":"2402.07752","title":"Mixed Q-Functionals: Advancing Value-Based Methods in Cooperative MARL with Continuous Action Domains","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2409.19391","title":"Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training","created":"2024-09-28","cited_by_count":1,"area":null},{"id":"2504.08417","title":"Belief States for Cooperative Multi-Agent Reinforcement Learning under Partial Observability","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2506.04265","title":"Cooperative Game-Theoretic Credit Assignment for Multi-Agent Policy Gradients via the Core","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2509.12117","title":"$K$-Level Policy Gradients for Multi-Agent Reinforcement Learning","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2510.11824","title":"Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.13343","title":"AOAD-MAT: Transformer-based multi-agent deep reinforcement learning model considering agents' order of action decisions","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2511.02762","title":"From Solo to Symphony: Orchestrating Multi-Agent Collaboration with Single-Agent Demos","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.07707","title":"A Negotiation-Based Multi-Agent Reinforcement Learning Approach for Dynamic Scheduling of Reconfigurable Manufacturing Systems","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2511.18181","title":"MOMA-AC: A preference-driven actor-critic framework for continuous multi-objective multi-agent reinforcement learning","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2602.06476","title":"Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2604.17693","title":"COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2210.12896","title":"Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learning","created":"2022-10-24","cited_by_count":0,"area":null},{"id":"2304.01447","title":"Off-Policy Action Anticipation in Multi-Agent Reinforcement Learning","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2305.17018","title":"Formal Modelling for Multi-Robot Systems Under Uncertainty","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2308.00629","title":"Dependency Structure Search Bayesian Optimization for Decision Making Models","created":"2023-08-01","cited_by_count":0,"area":null}],"next_cursor":"100"}