{"list":"other","total":59,"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":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"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":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"2112.13487","title":"The Statistical Complexity of Interactive Decision Making","created":"2021-12-27","cited_by_count":218},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"2012.08507","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2020-12-15","cited_by_count":200},{"id":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"2007.04938","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","created":"2020-07-09","cited_by_count":152},{"id":"1509.08731","title":"Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning","created":"2015-09-29","cited_by_count":144},{"id":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115},{"id":"2002.04017","title":"Provable Self-Play Algorithms for Competitive Reinforcement Learning","created":"2020-02-10","cited_by_count":113},{"id":"1912.04136","title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation","created":"2019-12-09","cited_by_count":111},{"id":"2006.12007","title":"Near-Optimal Reinforcement Learning with Self-Play","created":"2020-06-22","cited_by_count":109},{"id":"2010.01604","title":"A Sharp Analysis of Model-based Reinforcement Learning with Self-Play","created":"2020-10-04","cited_by_count":105},{"id":"1911.00567","title":"Frequentist Regret Bounds for Randomized Least-Squares Value Iteration","created":"2019-11-01","cited_by_count":101},{"id":"1910.10597","title":"Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles","created":"2019-10-23","cited_by_count":100},{"id":"2002.07066","title":"Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium","created":"2020-02-17","cited_by_count":100},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83},{"id":"1908.06976","title":"A survey on intrinsic motivation in reinforcement learning","created":"2019-08-19","cited_by_count":81},{"id":"2006.12484","title":"Sample-Efficient Reinforcement Learning of Undercomplete POMDPs","created":"2020-06-22","cited_by_count":66},{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66},{"id":"1705.07347","title":"Ensemble Sampling","created":"2017-05-20","cited_by_count":62},{"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":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48},{"id":"2107.14702","title":"Towards General Function Approximation in Zero-Sum Markov Games","created":"2021-07-30","cited_by_count":43},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32},{"id":"2208.10904","title":"A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning","created":"2022-08-23","cited_by_count":31},{"id":"2209.15634","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","created":"2022-09-30","cited_by_count":31},{"id":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30},{"id":"2305.08841","title":"A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes","created":"2023-05-15","cited_by_count":29},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28},{"id":"1811.01483","title":"Contingency-Aware Exploration in Reinforcement Learning","created":"2018-11-05","cited_by_count":26},{"id":"2205.13589","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","created":"2022-05-26","cited_by_count":26},{"id":"2205.13476","title":"Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency","created":"2022-05-26","cited_by_count":16},{"id":"2210.01907","title":"A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games","created":"2022-10-04","cited_by_count":16},{"id":"2011.07738","title":"Reward Biased Maximum Likelihood Estimation for Reinforcement Learning","created":"2020-11-16","cited_by_count":11},{"id":"2010.04091","title":"Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits","created":"2020-10-08","cited_by_count":9},{"id":"2201.10542","title":"Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems","created":"2022-01-25","cited_by_count":5}],"next_cursor":null}