{"total":23,"rows":[{"id":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36,"area":null},{"id":"2110.10116","title":"On the Global Optimum Convergence of Momentum-based Policy Gradient","created":"2021-10-19","cited_by_count":26,"area":null},{"id":"2209.10113","title":"Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning","created":"2022-09-20","cited_by_count":18,"area":null},{"id":"2105.08601","title":"Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection","created":"2021-05-18","cited_by_count":14,"area":null},{"id":"2101.03238","title":"Neurosymbolic Transformers for Multi-Agent Communication","created":"2021-01-05","cited_by_count":13,"area":null},{"id":"2109.12343","title":"Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems","created":"2021-09-25","cited_by_count":12,"area":null},{"id":"2112.09046","title":"Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach","created":"2021-12-16","cited_by_count":12,"area":null},{"id":"2111.01777","title":"A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies","created":"2021-11-02","cited_by_count":11,"area":null},{"id":"2103.13446","title":"ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecture","created":"2021-03-24","cited_by_count":9,"area":null},{"id":"2210.09378","title":"Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation","created":"2022-10-17","cited_by_count":8,"area":null},{"id":"2104.13868","title":"Communication Topology Co-Design in Graph Recurrent Neural Network Based Distributed Control","created":"2021-04-28","cited_by_count":7,"area":null},{"id":"2102.06284","title":"Large Scale Distributed Collaborative Unlabeled Motion Planning with Graph Policy Gradients","created":"2021-02-11","cited_by_count":5,"area":null},{"id":"2210.08408","title":"Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding","created":"2022-10-16","cited_by_count":5,"area":null},{"id":"2310.04294","title":"Graph learning in robotics: a survey","created":"2023-10-06","cited_by_count":5,"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":"2107.12254","title":"The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts","created":"2021-07-26","cited_by_count":4,"area":null},{"id":"2501.06058","title":"Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2307.13192","title":"Counterfactual Explanation Policies in RL","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2407.00494","title":"Graph Neural Networks Gone Hogwild","created":"2024-06-29","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":"2110.12144","title":"Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network","created":"2021-10-23","cited_by_count":0,"area":null},{"id":"2606.02107","title":"Network Distributed Multi-Agent Reinforcement Learning for Consensus Control of Quadcopters","created":"2026-06-01","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}],"next_cursor":null}