{"list":"other","total":98,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"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":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"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":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1810.02912","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","created":"2018-10-05","cited_by_count":261},{"id":"1701.01724","title":"DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker","created":"2017-01-06","cited_by_count":233},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"id":"1702.03037","title":"Multi-agent Reinforcement Learning in Sequential Social Dilemmas","created":"2017-02-10","cited_by_count":209},{"id":"1802.05438","title":"Mean Field Multi-Agent Reinforcement Learning","created":"2018-02-15","cited_by_count":207},{"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":"1612.07182","title":"Multi-Agent Cooperation and the Emergence of (Natural) Language","created":"2016-12-21","cited_by_count":185},{"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":"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":"1903.04527","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","created":"2019-03-11","cited_by_count":164},{"id":"1607.07086","title":"An Actor-Critic Algorithm for Sequence Prediction","created":"2016-07-24","cited_by_count":159},{"id":"1603.01121","title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","created":"2016-03-03","cited_by_count":158},{"id":"1712.06567","title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning","created":"2017-12-18","cited_by_count":150},{"id":"1709.08071","title":"Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems","created":"2017-09-23","cited_by_count":131},{"id":"1812.11794","title":"Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications","created":"2018-12-31","cited_by_count":127},{"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":"1708.05144","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","created":"2017-08-17","cited_by_count":121},{"id":"1609.03250","title":"DESPOT: Online POMDP Planning with Regularization","created":"2016-09-12","cited_by_count":106},{"id":"1803.08884","title":"Inequity aversion improves cooperation in intertemporal social dilemmas","created":"2018-03-23","cited_by_count":106},{"id":"1609.05559","title":"Opponent Modeling in Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":97},{"id":"1703.10069","title":"Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games","created":"2017-03-29","cited_by_count":96},{"id":"2011.00583","title":"Game-Theoretic Multiagent Reinforcement Learning","created":"2020-11-01","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":"1706.08502","title":"Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog","created":"2017-06-26","cited_by_count":86},{"id":"1703.06585","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","created":"2017-03-20","cited_by_count":71},{"id":"1903.05168","title":"On the Pitfalls of Measuring Emergent Communication","created":"2019-03-12","cited_by_count":71},{"id":"1901.09207","title":"Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning","created":"2019-01-26","cited_by_count":68},{"id":"1802.09756","title":"Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising","created":"2018-02-27","cited_by_count":65},{"id":"1804.03980","title":"Emergent Communication through Negotiation","created":"2018-04-11","cited_by_count":62},{"id":"1907.13220","title":"Multi-Agent Adversarial Inverse Reinforcement Learning","created":"2019-07-30","cited_by_count":60},{"id":"2011.03615","title":"Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial","created":"2020-11-06","cited_by_count":60},{"id":"1902.07151","title":"Emergent Coordination Through Competition","created":"2019-02-19","cited_by_count":57},{"id":"2011.04021","title":"On the role of planning in model-based deep reinforcement learning","created":"2020-11-08","cited_by_count":57},{"id":"1911.04175","title":"Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning","created":"2019-11-11","cited_by_count":53},{"id":"1902.01724","title":"AlphaStar: An Evolutionary Computation Perspective","created":"2019-02-05","cited_by_count":50},{"id":"2002.02325","title":"Social diversity and social preferences in mixed-motive reinforcement learning","created":"2020-02-06","cited_by_count":49},{"id":"1707.01068","title":"Maintaining cooperation in complex social dilemmas using deep reinforcement learning","created":"2017-07-04","cited_by_count":48},{"id":"2007.12306","title":"Value-Decomposition Multi-Agent Actor-Critics","created":"2020-07-24","cited_by_count":48},{"id":"1709.02865","title":"Prosocial learning agents solve generalized Stag Hunts better than selfish ones","created":"2017-09-08","cited_by_count":47},{"id":"1805.07830","title":"Learning to Teach in Cooperative Multiagent Reinforcement Learning","created":"2018-05-20","cited_by_count":45},{"id":"2106.02757","title":"Heuristic-Guided Reinforcement Learning","created":"2021-06-05","cited_by_count":42},{"id":"2002.06684","title":"R-MADDPG for Partially Observable Environments and Limited Communication","created":"2020-02-16","cited_by_count":36},{"id":"2006.01482","title":"Multi-Agent Determinantal Q-Learning","created":"2020-06-02","cited_by_count":36},{"id":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32},{"id":"1810.11702","title":"Multi-Agent Common Knowledge Reinforcement Learning","created":"2018-10-27","cited_by_count":31},{"id":"2007.15724","title":"MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments","created":"2020-07-30","cited_by_count":26},{"id":"1712.07893","title":"A Deep Policy Inference Q-Network for Multi-Agent Systems","created":"2017-12-21","cited_by_count":25},{"id":"1712.06568","title":"ES Is More Than Just a Traditional Finite-Difference Approximator","created":"2017-12-18","cited_by_count":24},{"id":"1903.08082","title":"Learning Reciprocity in Complex Sequential Social Dilemmas","created":"2019-03-19","cited_by_count":24},{"id":"2002.03950","title":"Q-value Path Decomposition for Deep Multiagent Reinforcement Learning","created":"2020-02-10","cited_by_count":24},{"id":"2102.02274","title":"Neural Recursive Belief States in Multi-Agent Reinforcement Learning","created":"2021-02-03","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":"1712.06564","title":"On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent","created":"2017-12-18","cited_by_count":16},{"id":"1611.03218","title":"Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence","created":"2016-11-10","cited_by_count":15},{"id":"1712.06563","title":"Safe Mutations for Deep and Recurrent Neural Networks through Output Gradients","created":"2017-12-18","cited_by_count":15},{"id":"1801.08116","title":"Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents","created":"2018-01-24","cited_by_count":15},{"id":"1906.11046","title":"Multi-Agent Deep Reinforcement Learning for Liquidation Strategy Analysis","created":"2019-06-24","cited_by_count":15},{"id":"1404.1140","title":"Scalable Planning and Learning for Multiagent POMDPs: Extended Version","created":"2014-04-04","cited_by_count":14},{"id":"1905.01357","title":"Teaching on a Budget in Multi-Agent Deep Reinforcement Learning","created":"2019-04-19","cited_by_count":14},{"id":"1906.07315","title":"Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination","created":"2019-06-18","cited_by_count":14},{"id":"2006.16679","title":"R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning in Games","created":"2020-06-30","cited_by_count":11},{"id":"1706.03235","title":"ACCNet: Actor-Coordinator-Critic Net for \"Learning-to-Communicate\" with Deep Multi-agent Reinforcement Learning","created":"2017-06-10","cited_by_count":8},{"id":"2003.10598","title":"Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward","created":"2020-03-24","cited_by_count":8},{"id":"2012.11258","title":"Difference Rewards Policy Gradients","created":"2020-12-21","cited_by_count":8},{"id":"1401.1549","title":"Optimal Demand Response Using Device Based Reinforcement Learning","created":"2014-01-08","cited_by_count":7},{"id":"2103.04289","title":"Learning Human Rewards by Inferring Their Latent Intelligence Levels in Multi-Agent Games: A Theory-of-Mind Approach with Application to Driving Data","created":"2021-03-07","cited_by_count":6},{"id":"1802.08534","title":"Weighted Double Deep Multiagent Reinforcement Learning in Stochastic Cooperative Environments","created":"2018-02-23","cited_by_count":5},{"id":"1803.00162","title":"Towards Cooperation in Sequential Prisoner's Dilemmas: a Deep Multiagent Reinforcement Learning Approach","created":"2018-03-01","cited_by_count":4},{"id":"1810.03679","title":"Multi-agent Deep Reinforcement Learning for Zero Energy Communities","created":"2018-10-08","cited_by_count":4},{"id":"1910.02240","title":"Attention-based Fault-tolerant Approach for Multi-agent Reinforcement Learning Systems","created":"2019-10-05","cited_by_count":3}],"next_cursor":null}