{"list":"other","total":68,"rows":[{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"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":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1905.05408","title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","created":"2019-05-14","cited_by_count":379},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"1703.04908","title":"Emergence of Grounded Compositional Language in Multi-Agent Populations","created":"2017-03-15","cited_by_count":263},{"id":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"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":"1511.08779","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","created":"2015-11-27","cited_by_count":184},{"id":"1810.05587","title":"A Survey and Critique of Multiagent Deep Reinforcement Learning","created":"2018-10-12","cited_by_count":177},{"id":"1805.07733","title":"Learning Attentional Communication for Multi-Agent Cooperation","created":"2018-05-20","cited_by_count":175},{"id":"2006.02419","title":"Emergent Multi-Agent Communication in the Deep Learning Era","created":"2020-06-03","cited_by_count":170},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"1705.11192","title":"Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols","created":"2017-05-31","cited_by_count":125},{"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":"1702.08887","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","created":"2017-02-28","cited_by_count":117},{"id":"2004.09124","title":"Compositionality and Generalization in Emergent Languages","created":"2020-04-20","cited_by_count":103},{"id":"2007.12322","title":"Off-Policy Multi-Agent Decomposed Policy Gradients","created":"2020-07-24","cited_by_count":98},{"id":"1902.01554","title":"Learning to Schedule Communication in Multi-agent Reinforcement Learning","created":"2019-02-05","cited_by_count":93},{"id":"1906.04737","title":"Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning","created":"2019-06-11","cited_by_count":93},{"id":"1910.05366","title":"Learning Nearly Decomposable Value Functions Via Communication Minimization","created":"2019-10-11","cited_by_count":86},{"id":"1911.10715","title":"Multi-Agent Game Abstraction via Graph Attention Neural Network","created":"2019-11-25","cited_by_count":82},{"id":"1903.05168","title":"On the Pitfalls of Measuring Emergent Communication","created":"2019-03-12","cited_by_count":71},{"id":"1804.03980","title":"Emergent Communication through Negotiation","created":"2018-04-11","cited_by_count":62},{"id":"1911.06992","title":"Learning Efficient Multi-agent Communication: An Information Bottleneck Approach","created":"2019-11-16","cited_by_count":61},{"id":"1905.12561","title":"Anti-efficient encoding in emergent communication","created":"2019-05-29","cited_by_count":59},{"id":"2006.06455","title":"Learning Individually Inferred Communication for Multi-Agent Cooperation","created":"2020-06-11","cited_by_count":55},{"id":"2004.01339","title":"Multi-agent Reinforcement Learning for Networked System Control","created":"2020-04-03","cited_by_count":53},{"id":"1912.05676","title":"Biases for Emergent Communication in Multi-agent Reinforcement Learning","created":"2019-12-11","cited_by_count":48},{"id":"1909.02682","title":"Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control","created":"2019-09-06","cited_by_count":46},{"id":"1906.01202","title":"Learning Transferable Cooperative Behavior in Multi-Agent Teams","created":"2019-06-04","cited_by_count":44},{"id":"2202.03390","title":"Geometric Multimodal Contrastive Representation Learning","created":"2022-02-07","cited_by_count":40},{"id":"2110.15349","title":"Learning to Ground Multi-Agent Communication with Autoencoders","created":"2021-10-28","cited_by_count":37},{"id":"1912.05304","title":"Learning Agent Communication under Limited Bandwidth by Message Pruning","created":"2019-12-03","cited_by_count":31},{"id":"1910.11424","title":"Capacity, Bandwidth, and Compositionality in Emergent Language Learning","created":"2019-10-24","cited_by_count":30},{"id":"2010.14391","title":"Succinct and Robust Multi-Agent Communication With Temporal Message Control","created":"2020-10-27","cited_by_count":29},{"id":"2002.04235","title":"Learning Structured Communication for Multi-agent Reinforcement Learning","created":"2020-02-11","cited_by_count":21},{"id":"2108.01828","title":"Emergent Discrete Communication in Semantic Spaces","created":"2021-08-04","cited_by_count":20},{"id":"2103.08067","title":"Quasi-Equivalence Discovery for Zero-Shot Emergent Communication","created":"2021-03-14","cited_by_count":19},{"id":"1809.00549","title":"Emergence of Communication in an Interactive World with Consistent Speakers","created":"2018-09-03","cited_by_count":18},{"id":"1901.03887","title":"Improving Coordination in Small-Scale Multi-Agent Deep Reinforcement Learning through Memory-driven Communication","created":"2019-01-12","cited_by_count":18},{"id":"2004.01097","title":"Learning to cooperate: Emergent communication in multi-agent navigation","created":"2020-04-02","cited_by_count":18},{"id":"2101.10276","title":"Emergent Communication under Competition","created":"2021-01-25","cited_by_count":18},{"id":"2108.03803","title":"Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning","created":"2021-08-09","cited_by_count":18},{"id":"1902.06527","title":"Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement Learning","created":"2019-02-18","cited_by_count":17},{"id":"2105.10716","title":"Attention-based Reinforcement Learning for Real-Time UAV Semantic Communication","created":"2021-05-22","cited_by_count":14},{"id":"1811.12557","title":"Deep Multi-Agent Reinforcement Learning with Relevance Graphs","created":"2018-11-30","cited_by_count":13},{"id":"2102.00824","title":"HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging","created":"2021-01-18","cited_by_count":13},{"id":"1611.00625","title":"TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games","created":"2016-11-01","cited_by_count":12},{"id":"1712.07305","title":"Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning","created":"2017-12-20","cited_by_count":12},{"id":"1812.00922","title":"Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations","created":"2018-12-03","cited_by_count":10},{"id":"2010.04978","title":"Event-Triggered Multi-agent Reinforcement Learning with Communication under Limited-bandwidth Constraint","created":"2020-10-10","cited_by_count":10},{"id":"2002.09604","title":"Emergent Communication with World Models","created":"2020-02-22","cited_by_count":7},{"id":"2201.11994","title":"FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems","created":"2022-01-28","cited_by_count":7},{"id":"1911.05438","title":"Learning to Communicate in Multi-Agent Reinforcement Learning : A Review","created":"2019-11-13","cited_by_count":6}],"next_cursor":null}