{"list":"other","total":130,"rows":[{"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":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"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":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"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":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"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":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"2106.13281","title":"Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulation","created":"2021-06-24","cited_by_count":407},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1605.07736","title":"Learning Multiagent Communication with Backpropagation","created":"2016-05-25","cited_by_count":366},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1610.03295","title":"Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving","created":"2016-10-11","cited_by_count":311},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"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":"1907.11180","title":"Google Research Football: A Novel Reinforcement Learning Environment","created":"2019-07-25","cited_by_count":260},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1709.04326","title":"Learning with Opponent-Learning Awareness","created":"2017-09-13","cited_by_count":222},{"id":"2009.14471","title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","created":"2020-09-30","cited_by_count":220},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"1311.1869","title":"Optimization, Learning, and Games with Predictable Sequences","created":"2013-11-08","cited_by_count":188},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1511.08779","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","created":"2015-11-27","cited_by_count":184},{"id":"1805.07733","title":"Learning Attentional Communication for Multi-Agent Cooperation","created":"2018-05-20","cited_by_count":175},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1903.04527","title":"Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control","created":"2019-03-11","cited_by_count":164},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"1810.09202","title":"Graph Convolutional Reinforcement Learning","created":"2018-10-22","cited_by_count":152},{"id":"1703.06182","title":"Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability","created":"2017-03-17","cited_by_count":148},{"id":"1901.08511","title":"A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach","created":"2019-01-24","cited_by_count":143},{"id":"1807.03858","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","created":"2018-07-10","cited_by_count":140},{"id":"1709.08071","title":"Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems","created":"2017-09-23","cited_by_count":131},{"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":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122},{"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":"1812.09755","title":"Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks","created":"2018-12-23","cited_by_count":121},{"id":"2010.09776","title":"SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving","created":"2020-10-19","cited_by_count":121},{"id":"2206.08686","title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","created":"2022-06-17","cited_by_count":119},{"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":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"id":"1807.03907","title":"The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization","created":"2018-07-11","cited_by_count":101},{"id":"1809.05214","title":"Model-Based Reinforcement Learning via Meta-Policy Optimization","created":"2018-09-14","cited_by_count":101},{"id":"1910.00091","title":"Deep Coordination Graphs","created":"2019-09-27","cited_by_count":98},{"id":"2007.12322","title":"Off-Policy Multi-Agent Decomposed Policy Gradients","created":"2020-07-24","cited_by_count":98},{"id":"1707.09183","title":"A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity","created":"2017-07-28","cited_by_count":94},{"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":"1911.02140","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","created":"2019-11-05","cited_by_count":88},{"id":"1703.02949","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","created":"2017-03-08","cited_by_count":85},{"id":"1911.10715","title":"Multi-Agent Game Abstraction via Graph Attention Neural Network","created":"2019-11-25","cited_by_count":82},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79},{"id":"1407.5042","title":"Solving Large Imperfect Information Games Using CFR+","created":"2014-07-18","cited_by_count":78},{"id":"1712.00600","title":"MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence","created":"2017-12-02","cited_by_count":71},{"id":"1903.05168","title":"On the Pitfalls of Measuring Emergent Communication","created":"2019-03-12","cited_by_count":71},{"id":"2101.07123","title":"Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint","created":"2021-01-18","cited_by_count":70},{"id":"2207.03530","title":"VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning","created":"2022-07-07","cited_by_count":68},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68},{"id":"1802.09640","title":"Modeling Others using Oneself in Multi-Agent Reinforcement Learning","created":"2018-02-26","cited_by_count":66},{"id":"1802.09756","title":"Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising","created":"2018-02-27","cited_by_count":65}],"next_cursor":"100"}