{"list":"other","total":73,"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1803.11485","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2018-03-30","cited_by_count":708},{"id":"1712.05889","title":"Ray: A Distributed Framework for Emerging AI Applications","created":"2017-12-16","cited_by_count":527},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"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":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2004.00784","title":"Learning Agile Robotic Locomotion Skills by Imitating Animals","created":"2020-04-02","cited_by_count":251},{"id":"1809.02627","title":"Unity: A General Platform for Intelligent Agents","created":"2018-09-07","cited_by_count":236},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"2009.14471","title":"PettingZoo: Gym for Multi-Agent Reinforcement Learning","created":"2020-09-30","cited_by_count":220},{"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":"1908.09453","title":"OpenSpiel: A Framework for Reinforcement Learning in Games","created":"2019-08-26","cited_by_count":186},{"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":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184},{"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":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143},{"id":"1812.06110","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","created":"2018-12-14","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":"2104.00683","title":"SimPoE: Simulated Character Control for 3D Human Pose Estimation","created":"2021-04-01","cited_by_count":114},{"id":"1810.05762","title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","created":"2018-10-12","cited_by_count":90},{"id":"1709.10082","title":"Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning","created":"2017-09-28","cited_by_count":83},{"id":"2002.03939","title":"Qatten: A General Framework for Cooperative Multiagent Reinforcement Learning","created":"2020-02-10","cited_by_count":81},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2006.07364","title":"Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis","created":"2020-06-12","cited_by_count":64},{"id":"1801.08093","title":"Learning Symmetric and Low-energy Locomotion","created":"2018-01-24","cited_by_count":61},{"id":"1902.06865","title":"Hyperbolic Discounting and Learning over Multiple Horizons","created":"2019-02-19","cited_by_count":60},{"id":"2005.04323","title":"ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills","created":"2020-05-09","cited_by_count":54},{"id":"2103.16021","title":"Fast and Feature-Complete Differentiable Physics for Articulated Rigid Bodies with Contact","created":"2021-03-30","cited_by_count":52},{"id":"1611.01055","title":"Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?","created":"2016-11-03","cited_by_count":48},{"id":"1807.06613","title":"Deep Reinforcement Learning for Swarm Systems","created":"2018-07-17","cited_by_count":45},{"id":"2007.02040","title":"Discount Factor as a Regularizer in Reinforcement Learning","created":"2020-07-04","cited_by_count":45},{"id":"2011.15119","title":"UniCon: Universal Neural Controller For Physics-based Character Motion","created":"2020-11-30","cited_by_count":40},{"id":"2003.14414","title":"Optical Non-Line-of-Sight Physics-based 3D Human Pose Estimation","created":"2020-03-31","cited_by_count":34},{"id":"2010.04304","title":"Learning to Locomote: Understanding How Environment Design Matters for Deep Reinforcement Learning","created":"2020-10-09","cited_by_count":27},{"id":"2011.04764","title":"Deep Reinforcement Learning for Navigation in AAA Video Games","created":"2020-11-09","cited_by_count":27},{"id":"2110.06901","title":"A Survey on Deep Learning for Skeleton-Based Human Animation","created":"2021-10-13","cited_by_count":27},{"id":"1904.13041","title":"Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation","created":"2019-04-30","cited_by_count":23},{"id":"1901.01291","title":"On the Utility of Model Learning in HRI","created":"2019-01-04","cited_by_count":21},{"id":"1804.00361","title":"Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments","created":"2018-04-02","cited_by_count":19},{"id":"1608.00627","title":"Learning Transferable Policies for Monocular Reactive MAV Control","created":"2016-08-01","cited_by_count":18},{"id":"1910.04281","title":"Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments","created":"2019-10-09","cited_by_count":17},{"id":"2105.00371","title":"Discovering Diverse Athletic Jumping Strategies","created":"2021-05-02","cited_by_count":16},{"id":"2103.16807","title":"Learning and Exploring Motor Skills with Spacetime Bounds","created":"2021-03-31","cited_by_count":9},{"id":"2103.10000","title":"Human-Inspired Multi-Agent Navigation using Knowledge Distillation","created":"2021-03-18","cited_by_count":7},{"id":"1804.00198","title":"Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning","created":"2018-03-31","cited_by_count":6},{"id":"2002.10221","title":"The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI","created":"2020-02-15","cited_by_count":6},{"id":"1703.02905","title":"Learning a Unified Control Policy for Safe Falling","created":"2017-03-08","cited_by_count":4},{"id":"1801.08391","title":"Understanding Human Behaviors in Crowds by Imitating the Decision-Making Process","created":"2018-01-25","cited_by_count":4},{"id":"2009.13051","title":"Agent Environment Cycle Games","created":"2020-09-28","cited_by_count":2}],"next_cursor":null}