{"list":"other","total":52,"rows":[{"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":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"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":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1810.08750","title":"Learning Models with Uniform Performance via Distributionally Robust Optimization","created":"2018-10-20","cited_by_count":335},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1807.02582","title":"Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences","created":"2018-07-06","cited_by_count":192},{"id":"1906.03804","title":"Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal","created":"2019-06-10","cited_by_count":127},{"id":"1911.07676","title":"Learning with Good Feature Representations in Bandits and in RL with a Generative Model","created":"2019-11-18","cited_by_count":127},{"id":"2005.12900","title":"Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model","created":"2020-05-26","cited_by_count":109},{"id":"1809.05214","title":"Model-Based Reinforcement Learning via Meta-Policy Optimization","created":"2018-09-14","cited_by_count":101},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"id":"2008.06389","title":"Sample-efficient Cross-Entropy Method for Real-time Planning","created":"2020-08-14","cited_by_count":95},{"id":"2006.12466","title":"Information Theoretic Regret Bounds for Online Nonlinear Control","created":"2020-06-22","cited_by_count":90},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89},{"id":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87},{"id":"2006.08684","title":"Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning","created":"2020-06-15","cited_by_count":86},{"id":"2112.01506","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","created":"2021-12-02","cited_by_count":83},{"id":"1906.07516","title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification","created":"2019-06-18","cited_by_count":78},{"id":"1810.10775","title":"Adversarially Robust Optimization with Gaussian Processes","created":"2018-10-25","cited_by_count":62},{"id":"2002.09038","title":"Distributionally Robust Bayesian Optimization","created":"2020-02-20","cited_by_count":61},{"id":"1610.03518","title":"Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model","created":"2016-10-11","cited_by_count":54},{"id":"2108.09262","title":"Optimal Order Simple Regret for Gaussian Process Bandits","created":"2021-08-20","cited_by_count":54},{"id":"1706.04711","title":"Reinforcement Learning under Model Mismatch","created":"2017-06-15","cited_by_count":52},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51},{"id":"2303.02783","title":"Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning","created":"2023-03-05","cited_by_count":44},{"id":"1902.07605","title":"Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs","created":"2019-02-20","cited_by_count":40},{"id":"1803.04848","title":"Soft-Robust Actor-Critic Policy-Gradient","created":"2018-03-11","cited_by_count":37},{"id":"2302.13203","title":"A Finite Sample Complexity Bound for Distributionally Robust Q-learning","created":"2023-02-26","cited_by_count":36},{"id":"1911.01871","title":"On Online Learning in Kernelized Markov Decision Processes","created":"2019-11-04","cited_by_count":35},{"id":"1905.08188","title":"A Bayesian Approach to Robust Reinforcement Learning","created":"2019-05-20","cited_by_count":34},{"id":"1501.07418","title":"Distributionally Robust Counterpart in Markov Decision Processes","created":"2015-01-29","cited_by_count":33},{"id":"2305.18420","title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","created":"2023-05-28","cited_by_count":29},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","cited_by_count":27},{"id":"2108.05533","title":"Efficient Local Planning with Linear Function Approximation","created":"2021-08-12","cited_by_count":23},{"id":"2302.05372","title":"Towards Minimax Optimality of Model-based Robust Reinforcement Learning","created":"2023-02-10","cited_by_count":22},{"id":"1905.11957","title":"Sample Complexity of Sample Average Approximation for Conditional Stochastic Optimization","created":"2019-05-28","cited_by_count":19},{"id":"2007.06184","title":"Efficient Planning in Large MDPs with Weak Linear Function Approximation","created":"2020-07-13","cited_by_count":17},{"id":"1707.07907","title":"Mutual Alignment Transfer Learning","created":"2017-07-25","cited_by_count":16},{"id":"2112.05244","title":"An Experimental Design Perspective on Model-Based Reinforcement Learning","created":"2021-12-09","cited_by_count":16},{"id":"2301.11721","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","created":"2023-01-27","cited_by_count":16},{"id":"2001.06814","title":"Distributionally Robust Bayesian Quadrature Optimization","created":"2020-01-19","cited_by_count":15},{"id":"2103.10369","title":"Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning","created":"2021-03-18","cited_by_count":14},{"id":"2205.14278","title":"Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization","created":"2022-05-28","cited_by_count":7},{"id":"2212.09510","title":"Near-optimal Policy Identification in Active Reinforcement Learning","created":"2022-12-19","cited_by_count":7},{"id":"2302.04376","title":"Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning","created":"2023-02-08","cited_by_count":6},{"id":"2308.11139","title":"Rectangularity and duality of distributionally robust Markov Decision Processes","created":"2023-08-22","cited_by_count":6}],"next_cursor":null}