{"total":28,"rows":[{"id":"2305.17352","title":"Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2501.13200","title":"SRMT: Shared Memory for Multi-agent Lifelong Pathfinding","created":"2025-01-22","cited_by_count":8,"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":"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":"2410.14916","title":"Cooperation and Fairness in Multi-Agent Reinforcement Learning","created":"2024-10-19","cited_by_count":5,"area":null},{"id":"2410.07287","title":"Crafting Desirable Climate Trajectories with RL Explored Socio-Environmental Simulations","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2506.11285","title":"Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamwork","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2306.12926","title":"Decentralized Multi-Agent Reinforcement Learning with Global State Prediction","created":"2023-06-22","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":"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":"2507.23604","title":"Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2501.01136","title":"Symmetries-enhanced Multi-Agent Reinforcement Learning","created":"2025-01-02","cited_by_count":1,"area":null},{"id":"2501.13727","title":"Scalable Safe Multi-Agent Reinforcement Learning for Multi-Agent System","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2601.11401","title":"Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2309.10275","title":"Optimizing Crowd-Aware Multi-Agent Path Finding through Local Communication with Graph Neural Networks","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2505.09756","title":"LOD: Latent Objective Discovery in Heterogeneous Multi-Agent Reinforcement Learning","created":"2025-05-14","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":"2509.23960","title":"MAD-PINN: A Decentralized Physics-Informed Machine Learning Framework for Safe and Optimal Multi-Agent Control","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2510.09937","title":"Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspective","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2511.11992","title":"Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2512.24827","title":"Inter-Agent Relative Representations for Multi-Agent Option Discovery","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2604.03785","title":"Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learning","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.08391","title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.23585","title":"Decentralized Autonomous Traffic Management through Corridor Networks","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.23832","title":"Decentralized Coordination of Autonomous Traffic Through Advanced Air Mobility Corridors","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.24010","title":"Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.09422","title":"Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2610.10302","title":"Continual Graph Multi-Agent Reinforcement Learning","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}