{"list":"other","total":53,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"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":"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":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"1901.11275","title":"A Theory of Regularized Markov Decision Processes","created":"2019-01-31","cited_by_count":286},{"id":"2006.15134","title":"Critic Regularized Regression","created":"2020-06-26","cited_by_count":275},{"id":"1606.02647","title":"Safe and Efficient Off-Policy Reinforcement Learning","created":"2016-06-08","cited_by_count":264},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215},{"id":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190},{"id":"2005.04269","title":"Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics","created":"2020-05-08","cited_by_count":165},{"id":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138},{"id":"1512.08562","title":"Taming the Noise in Reinforcement Learning via Soft Updates","created":"2015-12-28","cited_by_count":127},{"id":"1711.00123","title":"Backpropagation through the Void: Optimizing control variates for black-box gradient estimation","created":"2017-10-31","cited_by_count":106},{"id":"1611.02796","title":"Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control","created":"2016-11-09","cited_by_count":101},{"id":"1708.04133","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","created":"2017-08-10","cited_by_count":93},{"id":"1909.12238","title":"V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control","created":"2019-09-26","cited_by_count":85},{"id":"1609.00150","title":"Reward Augmented Maximum Likelihood for Neural Structured Prediction","created":"2016-09-01","cited_by_count":81},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"1803.07246","title":"Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines","created":"2018-03-20","cited_by_count":68},{"id":"1912.03905","title":"ChainerRL: A Deep Reinforcement Learning Library","created":"2019-12-09","cited_by_count":51},{"id":"1802.10031","title":"The Mirage of Action-Dependent Baselines in Reinforcement Learning","created":"2018-02-27","cited_by_count":48},{"id":"1706.00387","title":"Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning","created":"2017-06-01","cited_by_count":40},{"id":"1907.04202","title":"Variational Inference MPC for Bayesian Model-based Reinforcement Learning","created":"2019-07-08","cited_by_count":39},{"id":"2003.14089","title":"Leverage the Average: an Analysis of KL Regularization in RL","created":"2020-03-31","cited_by_count":33},{"id":"1812.02256","title":"Relative Entropy Regularized Policy Iteration","created":"2018-12-05","cited_by_count":32},{"id":"2009.01791","title":"Action and Perception as Divergence Minimization","created":"2020-09-03","cited_by_count":32},{"id":"2001.00805","title":"Making Sense of Reinforcement Learning and Probabilistic Inference","created":"2020-01-03","cited_by_count":30},{"id":"1801.03326","title":"Expected Policy Gradients for Reinforcement Learning","created":"2018-01-10","cited_by_count":28},{"id":"1811.01132","title":"VIREL: A Variational Inference Framework for Reinforcement Learning","created":"2018-11-03","cited_by_count":22},{"id":"1611.09321","title":"Improving Policy Gradient by Exploring Under-appreciated Rewards","created":"2016-11-28","cited_by_count":14},{"id":"2006.07549","title":"Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning","created":"2020-06-13","cited_by_count":12}],"next_cursor":null}