{"list":"other","total":62,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"1912.05830","title":"Provably Efficient Exploration in Policy Optimization","created":"2019-12-12","cited_by_count":205},{"id":"1901.00210","title":"Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds","created":"2019-01-01","cited_by_count":195},{"id":"2002.02794","title":"Reward-Free Exploration for Reinforcement Learning","created":"2020-02-07","cited_by_count":177},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158},{"id":"1906.03804","title":"Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal","created":"2019-06-10","cited_by_count":127},{"id":"2004.10019","title":"Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition","created":"2020-04-21","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":"1510.08906","title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning","created":"2015-10-29","cited_by_count":106},{"id":"2010.03531","title":"Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited","created":"2020-10-07","cited_by_count":106},{"id":"1905.03814","title":"Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs","created":"2019-05-09","cited_by_count":105},{"id":"2009.13503","title":"Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon","created":"2020-09-28","cited_by_count":99},{"id":"2002.00260","title":"Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning","created":"2020-02-01","cited_by_count":96},{"id":"2006.03041","title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","created":"2020-06-04","cited_by_count":95},{"id":"2102.06548","title":"Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis","created":"2021-02-12","cited_by_count":92},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85},{"id":"2204.05275","title":"Settling the Sample Complexity of Model-Based Offline Reinforcement Learning","created":"2022-04-11","cited_by_count":83},{"id":"1811.03056","title":"Policy Certificates: Towards Accountable Reinforcement Learning","created":"2018-11-07","cited_by_count":81},{"id":"1905.12849","title":"Provably Efficient Q-Learning with Low Switching Cost","created":"2019-05-30","cited_by_count":78},{"id":"1905.06265","title":"Stochastic approximation with cone-contractive operators: Sharp $\\ell_\\infty$-bounds for $Q$-learning","created":"2019-05-15","cited_by_count":77},{"id":"1906.04697","title":"Variance-reduced $Q$-learning is minimax optimal","created":"2019-06-11","cited_by_count":73},{"id":"1802.04020","title":"Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning","created":"2018-02-12","cited_by_count":66},{"id":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65},{"id":"2006.09118","title":"$Q$-learning with Logarithmic Regret","created":"2020-06-16","cited_by_count":60},{"id":"1710.09988","title":"Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes","created":"2017-10-27","cited_by_count":57},{"id":"1906.02870","title":"Worst-Case Regret Bounds for Exploration via Randomized Value Functions","created":"2019-06-07","cited_by_count":57},{"id":"1901.09311","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","created":"2019-01-27","cited_by_count":55},{"id":"2110.04645","title":"Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning","created":"2021-10-09","cited_by_count":53},{"id":"2007.01891","title":"A Unifying View of Optimism in Episodic Reinforcement Learning","created":"2020-07-03","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":"2006.08040","title":"Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs","created":"2020-06-14","cited_by_count":51},{"id":"2102.04692","title":"Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap","created":"2021-02-09","cited_by_count":49},{"id":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46},{"id":"1803.01626","title":"Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs","created":"2018-03-05","cited_by_count":43},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42},{"id":"2302.10371","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","created":"2023-02-21","cited_by_count":40},{"id":"1905.11527","title":"Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies","created":"2019-05-27","cited_by_count":39},{"id":"2112.03432","title":"First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach","created":"2021-12-07","cited_by_count":38},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36},{"id":"2005.00527","title":"Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?","created":"2020-05-01","cited_by_count":35},{"id":"2104.11186","title":"Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret","created":"2021-04-22","cited_by_count":34},{"id":"2107.01264","title":"Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning","created":"2021-07-02","cited_by_count":34},{"id":"2006.03864","title":"Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity","created":"2020-06-06","cited_by_count":28},{"id":"2203.12922","title":"Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies","created":"2022-03-24","cited_by_count":27},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27},{"id":"2106.08377","title":"Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path","created":"2021-06-15","cited_by_count":23},{"id":"2301.13446","title":"Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments","created":"2023-01-31","cited_by_count":19},{"id":"2111.00633","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","created":"2021-11-01","cited_by_count":18},{"id":"1802.03386","title":"Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits","created":"2018-02-09","cited_by_count":17},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15},{"id":"2106.13013","title":"A Fully Problem-Dependent Regret Lower Bound for Finite-Horizon MDPs","created":"2021-06-24","cited_by_count":15},{"id":"2208.10458","title":"Minimax-Optimal Multi-Agent RL in Markov Games With a Generative Model","created":"2022-08-22","cited_by_count":15},{"id":"2304.07278","title":"Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning","created":"2023-04-14","cited_by_count":15},{"id":"2011.14267","title":"Minimax Sample Complexity for Turn-based Stochastic Game","created":"2020-11-29","cited_by_count":13},{"id":"2206.00177","title":"On Gap-dependent Bounds for Offline Reinforcement Learning","created":"2022-06-01","cited_by_count":13},{"id":"2305.15546","title":"Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time","created":"2023-05-24","cited_by_count":8}],"next_cursor":null}