{"total":48,"rows":[{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"area":null},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2301.07137","title":"Heterogeneous Multi-Robot Reinforcement Learning","created":"2023-01-17","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":"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":"2305.02128","title":"System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning","created":"2023-05-03","cited_by_count":14,"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":"2502.03640","title":"Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control","created":"2025-02-05","cited_by_count":8,"area":null},{"id":"2308.05893","title":"Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding","created":"2023-08-11","cited_by_count":6,"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":"2509.20648","title":"Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration","created":"2025-09-25","cited_by_count":4,"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":"2406.02890","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2408.07644","title":"SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning","created":"2024-08-14","cited_by_count":3,"area":null},{"id":"2502.15425","title":"TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning","created":"2025-02-21","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":"2507.23604","title":"Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2508.12845","title":"CAMAR: Continuous Actions Multi-Agent Routing","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2511.04904","title":"Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2512.15379","title":"Remotely Detectable Robot Policy Watermarking","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2606.08729","title":"IR-SIM: A Lightweight Declarative Simulator for Navigation Learning and Benchmarking","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2408.16875","title":"Learning Multi-agent Multi-machine Tending by Mobile Robots","created":"2024-08-29","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":"2601.08327","title":"Safe Heterogeneous Multi-Agent RL with Communication Regularization for Coordinated Target Acquisition","created":"2026-01-13","cited_by_count":1,"area":null},{"id":"2603.29999","title":"Phyelds: A Pythonic Framework for Aggregate Computing","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.12388","title":"Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2403.06750","title":"Generalising Multi-Agent Cooperation through Task-Agnostic Communication","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2406.05071","title":"Massively Multiagent Minigames for Training Generalist Agents","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2410.19761","title":"Physical Simulation for Multi-agent Multi-machine Tending","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2505.22753","title":"Enhancing Lifelong Multi-Agent Path-finding by Using Artificial Potential Fields","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.22609","title":"Ludax: A GPU-Accelerated Domain Specific Language for Board Games","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2507.19151","title":"ReCoDe: Reinforcement Learning-based Dynamic Constraint Design for Multi-Agent Coordination","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2507.21638","title":"Assistax: A Multi-Agent Hardware-Accelerated Reinforcement Learning Benchmark for Assistive Robotics","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2510.17261","title":"High-Level Multi-Robot Trajectory Planning And Spurious Behavior Detection","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2603.04659","title":"GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.05020","title":"Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.21085","title":"Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.26286","title":"Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.31318","title":"Generalized Intention Modeling in Multi-Agent Reinforcement Learning","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.02027","title":"World-Task Factorization for Robot Learning","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.09610","title":"Shape Formation for the Cooperative Transportation of Arbitrary Objects Using Multi-Agent Reinforcement Learning","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.38889","title":"VERA: Verifiable Feasibility Representations with Counterfactual Credit for Constrained Multi-Agent Control","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.02370","title":"Network-in-the-Loop at Scale: GPU-Batched 5G Simulation for Massively Parallel Robot Learning","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.13737","title":"SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18808","title":"Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}