{"list":"other","total":54,"rows":[{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"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":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","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":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"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":"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":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178},{"id":"1901.09018","title":"Provably efficient RL with Rich Observations via Latent State Decoding","created":"2019-01-25","cited_by_count":169},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129},{"id":"1912.04136","title":"Optimism in Reinforcement Learning with Generalized Linear Function Approximation","created":"2019-12-09","cited_by_count":111},{"id":"2010.03531","title":"Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited","created":"2020-10-07","cited_by_count":106},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","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":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91},{"id":"1912.01192","title":"Learning Adversarial MDPs with Bandit Feedback and Unknown Transition","created":"2019-12-03","cited_by_count":85},{"id":"2102.07035","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","created":"2021-02-14","cited_by_count":82},{"id":"1602.07182","title":"Explore First, Exploit Next: The True Shape of Regret in Bandit Problems","created":"2016-02-23","cited_by_count":79},{"id":"1905.07773","title":"Online Convex Optimization in Adversarial Markov Decision Processes","created":"2019-05-19","cited_by_count":79},{"id":"2002.08243","title":"Optimistic Policy Optimization with Bandit Feedback","created":"2020-02-19","cited_by_count":79},{"id":"2011.11566","title":"Logarithmic Regret for Reinforcement Learning with Linear Function Approximation","created":"2020-11-23","cited_by_count":79},{"id":"1803.00606","title":"On Oracle-Efficient PAC RL with Rich Observations","created":"2018-03-01","cited_by_count":71},{"id":"2010.01374","title":"Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions","created":"2020-10-03","cited_by_count":71},{"id":"2212.06132","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","created":"2022-12-12","cited_by_count":57},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52},{"id":"2205.11507","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","created":"2022-05-23","cited_by_count":52},{"id":"2202.00063","title":"Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach","created":"2022-01-31","cited_by_count":51},{"id":"2106.07841","title":"Randomized Exploration for Reinforcement Learning with General Value Function Approximation","created":"2021-06-15","cited_by_count":49},{"id":"2006.05606","title":"Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition","created":"2020-06-10","cited_by_count":48},{"id":"2101.12745","title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","created":"2021-01-29","cited_by_count":45},{"id":"2010.00587","title":"Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs","created":"2020-10-01","cited_by_count":42},{"id":"2106.04117","title":"The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition","created":"2021-06-08","cited_by_count":40},{"id":"2007.01612","title":"Online learning in MDPs with linear function approximation and bandit feedback","created":"2020-07-03","cited_by_count":30},{"id":"2206.11489","title":"Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation","created":"2022-06-23","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":"2006.11561","title":"Stochastic Shortest Path with Adversarially Changing Costs","created":"2020-06-20","cited_by_count":28},{"id":"2102.08940","title":"Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs","created":"2021-02-17","cited_by_count":28},{"id":"2012.04053","title":"Minimax Regret for Stochastic Shortest Path with Adversarial Costs and Known Transition","created":"2020-12-07","cited_by_count":27},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24},{"id":"2110.12727","title":"Learning Stochastic Shortest Path with Linear Function Approximation","created":"2021-10-25","cited_by_count":23},{"id":"2301.12942","title":"Refined Regret for Adversarial MDPs with Linear Function Approximation","created":"2023-01-30","cited_by_count":19},{"id":"2102.07301","title":"Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation","created":"2021-02-15","cited_by_count":18},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18},{"id":"2205.13451","title":"Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback","created":"2022-05-26","cited_by_count":17},{"id":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","cited_by_count":17},{"id":"1905.12425","title":"Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalities","created":"2019-05-27","cited_by_count":15},{"id":"2210.16976","title":"Representation Learning for General-sum Low-rank Markov Games","created":"2022-10-30","cited_by_count":15},{"id":"2302.06834","title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","created":"2023-02-14","cited_by_count":15},{"id":"2303.10859","title":"Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs","created":"2023-03-20","cited_by_count":14},{"id":"2202.03334","title":"Policy Optimization for Stochastic Shortest Path","created":"2022-02-07","cited_by_count":13}],"next_cursor":null}