{"list":"other","total":90,"rows":[{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"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":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"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":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"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":"2006.10800","title":"Weighted QMIX: Expanding Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-06-18","cited_by_count":197},{"id":"2005.12729","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","created":"2020-05-25","cited_by_count":186},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"1910.07483","title":"MAVEN: Multi-Agent Variational Exploration","created":"2019-10-16","cited_by_count":185},{"id":"1511.08779","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","created":"2015-11-27","cited_by_count":184},{"id":"2003.06709","title":"FACMAC: Factored Multi-Agent Centralised Policy Gradients","created":"2020-03-14","cited_by_count":178},{"id":"1909.03004","title":"Show Your Work: Improved Reporting of Experimental Results","created":"2019-09-06","cited_by_count":169},{"id":"2006.05990","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","created":"2020-06-10","cited_by_count":162},{"id":"1703.06182","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","created":"2017-03-17","cited_by_count":148},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"2010.01523","title":"RODE: Learning Roles to Decompose Multi-Agent Tasks","created":"2020-10-04","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":"2006.07169","title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","created":"2020-06-12","cited_by_count":116},{"id":"2107.06857","title":"Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot","created":"2021-07-14","cited_by_count":99},{"id":"1910.00091","title":"Deep Coordination Graphs","created":"2019-09-27","cited_by_count":98},{"id":"2106.02195","title":"Celebrating Diversity in Shared Multi-Agent Reinforcement Learning","created":"2021-06-04","cited_by_count":98},{"id":"2011.00583","title":"Game-Theoretic Multiagent Reinforcement Learning","created":"2020-11-01","cited_by_count":94},{"id":"1708.04133","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","created":"2017-08-10","cited_by_count":93},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"2102.07475","title":"Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing","created":"2021-02-15","cited_by_count":87},{"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":"1910.05512","title":"Influence-Based Multi-Agent Exploration","created":"2019-10-12","cited_by_count":75},{"id":"1907.05707","title":"Shapley Q-value: A Local Reward Approach to Solve Global Reward Games","created":"2019-07-11","cited_by_count":73},{"id":"2102.03479","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-06","cited_by_count":68},{"id":"1806.08295","title":"How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments","created":"2018-06-21","cited_by_count":60},{"id":"2006.11438","title":"Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning","created":"2020-06-19","cited_by_count":60},{"id":"2111.09189","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","created":"2021-10-15","cited_by_count":58},{"id":"2107.11444","title":"Cooperative Exploration for Multi-Agent Deep Reinforcement Learning","created":"2021-07-23","cited_by_count":57},{"id":"2006.06455","title":"Learning Individually Inferred Communication for Multi-Agent Cooperation","created":"2020-06-11","cited_by_count":55},{"id":"1903.01373","title":"$\\alpha$-Rank: Multi-Agent Evaluation by Evolution","created":"2019-03-04","cited_by_count":51},{"id":"1912.05663","title":"Measuring the Reliability of Reinforcement Learning Algorithms","created":"2019-12-10","cited_by_count":51},{"id":"2111.11032","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","created":"2021-11-22","cited_by_count":49},{"id":"1912.02288","title":"Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning","created":"2019-12-04","cited_by_count":48},{"id":"2007.12306","title":"Value-Decomposition Multi-Agent Actor-Critics","created":"2020-07-24","cited_by_count":48},{"id":"1911.00025","title":"PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning","created":"2019-10-31","cited_by_count":47},{"id":"1909.02682","title":"Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control","created":"2019-09-06","cited_by_count":46},{"id":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45},{"id":"1906.01202","title":"Learning Transferable Cooperative Behavior in Multi-Agent Teams","created":"2019-06-04","cited_by_count":44},{"id":"1802.05054","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","created":"2018-02-14","cited_by_count":40},{"id":"2006.16958","title":"Evaluating the Performance of Reinforcement Learning Algorithms","created":"2020-06-30","cited_by_count":36},{"id":"2012.05893","title":"Flatland-RL : Multi-Agent Reinforcement Learning on Trains","created":"2020-12-10","cited_by_count":32},{"id":"1810.11702","title":"Multi-Agent Common Knowledge Reinforcement Learning","created":"2018-10-27","cited_by_count":31},{"id":"2010.14391","title":"Succinct and Robust Multi-Agent Communication With Temporal Message Control","created":"2020-10-27","cited_by_count":29},{"id":"1904.06979","title":"A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms","created":"2019-04-15","cited_by_count":27},{"id":"1804.09817","title":"Multiagent Soft Q-Learning","created":"2018-04-25","cited_by_count":26},{"id":"2006.00587","title":"Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization","created":"2020-05-31","cited_by_count":26},{"id":"2102.07936","title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","created":"2021-02-16","cited_by_count":26},{"id":"2111.04613","title":"Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems","created":"2021-11-08","cited_by_count":26},{"id":"2006.05842","title":"The Emergence of Individuality","created":"2020-06-10","cited_by_count":22},{"id":"1811.07029","title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG","created":"2018-11-13","cited_by_count":20},{"id":"1907.11461","title":"Action Semantics Network: Considering the Effects of Actions in Multiagent Systems","created":"2019-07-26","cited_by_count":19},{"id":"2010.13110","title":"Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks","created":"2020-10-25","cited_by_count":19},{"id":"2103.11883","title":"Regularized Softmax Deep Multi-Agent $Q$-Learning","created":"2021-03-22","cited_by_count":19},{"id":"2010.08531","title":"Multi-Agent Collaboration via Reward Attribution Decomposition","created":"2020-10-16","cited_by_count":17},{"id":"1911.04094","title":"SMIX($\\lambda$): Enhancing Centralized Value Functions for Cooperative Multi-Agent Reinforcement Learning","created":"2019-11-11","cited_by_count":15},{"id":"1909.09849","title":"Multiagent Evaluation under Incomplete Information","created":"2019-09-21","cited_by_count":13},{"id":"2112.09012","title":"Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation","created":"2021-12-16","cited_by_count":13},{"id":"1910.08809","title":"A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning","created":"2019-10-19","cited_by_count":10},{"id":"2112.02618","title":"LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning","created":"2021-12-05","cited_by_count":10},{"id":"2201.01221","title":"A Deeper Understanding of State-Based Critics in Multi-Agent Reinforcement Learning","created":"2022-01-03","cited_by_count":10},{"id":"2106.11652","title":"MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning","created":"2021-06-22","cited_by_count":6},{"id":"2112.00424","title":"Multi-Agent Transfer Learning in Reinforcement Learning-Based Ride-Sharing Systems","created":"2021-12-01","cited_by_count":6},{"id":"2012.12062","title":"QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning","created":"2020-12-22","cited_by_count":5},{"id":"2111.01100","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","created":"2021-11-01","cited_by_count":5},{"id":"2012.09762","title":"MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning","created":"2020-12-17","cited_by_count":4},{"id":"2110.08642","title":"Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning","created":"2021-10-16","cited_by_count":3},{"id":"2111.14177","title":"Evaluating Generalization and Transfer Capacity of Multi-Agent Reinforcement Learning Across Variable Number of Agents","created":"2021-11-28","cited_by_count":3},{"id":"2111.11229","title":"Off-Policy Correction For Multi-Agent Reinforcement Learning","created":"2021-11-22","cited_by_count":2}],"next_cursor":null}