{"list":"other","total":61,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"1905.05178","title":"Graph U-Nets","created":"2019-05-11","cited_by_count":492},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"2006.07869","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","created":"2020-06-14","cited_by_count":212},{"id":"1810.11187","title":"TarMAC: Targeted Multi-Agent Communication","created":"2018-10-26","cited_by_count":208},{"id":"1805.07733","title":"Learning Attentional Communication for Multi-Agent Cooperation","created":"2018-05-20","cited_by_count":175},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122},{"id":"1812.09755","title":"Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks","created":"2018-12-23","cited_by_count":121},{"id":"1912.12693","title":"A Gentle Introduction to Deep Learning for Graphs","created":"2019-12-29","cited_by_count":108},{"id":"2203.08975","title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","created":"2022-03-16","cited_by_count":104},{"id":"1707.09183","title":"A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity","created":"2017-07-28","cited_by_count":94},{"id":"1906.04737","title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","created":"2019-06-11","cited_by_count":93},{"id":"2010.01856","title":"My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control","created":"2020-10-05","cited_by_count":70},{"id":"2110.05292","title":"Understanding Pooling in Graph Neural Networks","created":"2021-10-11","cited_by_count":69},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68},{"id":"2006.11438","title":"Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning","created":"2020-06-19","cited_by_count":60},{"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},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48},{"id":"1506.01170","title":"A Game-Theoretic Model and Best-Response Learning Method for Ad Hoc Coordination in Multiagent Systems","created":"2015-06-03","cited_by_count":44},{"id":"1906.01202","title":"Learning Transferable Cooperative Behavior in Multi-Agent Teams","created":"2019-06-04","cited_by_count":44},{"id":"1912.03558","title":"Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery","created":"2019-12-07","cited_by_count":43},{"id":"1910.04450","title":"Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards","created":"2019-10-10","cited_by_count":40},{"id":"2312.01058","title":"A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment","created":"2023-12-02","cited_by_count":39},{"id":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36},{"id":"2301.07137","title":"Heterogeneous Multi-Robot Reinforcement Learning","created":"2023-01-17","cited_by_count":36},{"id":"1901.08492","title":"Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning","created":"2019-01-24","cited_by_count":33},{"id":"1909.12557","title":"Multi-Agent Actor-Critic with Hierarchical Graph Attention Network","created":"2019-09-27","cited_by_count":33},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33},{"id":"2212.11498","title":"Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers","created":"2022-12-22","cited_by_count":30},{"id":"1907.03822","title":"Graph Policy Gradients for Large Scale Robot Control","created":"2019-07-08","cited_by_count":28},{"id":"2503.13415","title":"A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives","created":"2025-03-17","cited_by_count":27},{"id":"2110.07246","title":"HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism","created":"2021-10-14","cited_by_count":19},{"id":"2505.15547","title":"Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning","created":"2025-05-21","cited_by_count":19},{"id":"2305.17352","title":"Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?","created":"2023-05-27","cited_by_count":18},{"id":"2404.10976","title":"Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning","created":"2024-04-17","cited_by_count":18},{"id":"2010.04740","title":"Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning","created":"2020-10-09","cited_by_count":14},{"id":"2205.13005","title":"QGNN: Value Function Factorisation with Graph Neural Networks","created":"2022-05-25","cited_by_count":14},{"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},{"id":"2208.05470","title":"EvolveHypergraph: Group-Aware Dynamic Relational Reasoning for Trajectory Prediction","created":"2022-08-10","cited_by_count":10},{"id":"2408.14597","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","created":"2024-08-26","cited_by_count":10},{"id":"2403.19253","title":"Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning","created":"2024-03-28","cited_by_count":7},{"id":"2304.05099","title":"Feudal Graph Reinforcement Learning","created":"2023-04-11","cited_by_count":4},{"id":"2205.13836","title":"Feudal Multi-Agent Reinforcement Learning with Adaptive Network Partition for Traffic Signal Control","created":"2022-05-27","cited_by_count":3},{"id":"2505.07207","title":"HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning","created":"2025-05-12","cited_by_count":3}],"next_cursor":null}