{"list":"other","total":54,"rows":[{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"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":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"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":"2004.10019","title":"Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition","created":"2020-04-21","cited_by_count":127},{"id":"1406.1853","title":"Model-based Reinforcement Learning and the Eluder Dimension","created":"2014-06-07","cited_by_count":116},{"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":"1910.07072","title":"Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes","created":"2019-10-15","cited_by_count":82},{"id":"1905.12849","title":"Provably Efficient Q-Learning with Low Switching Cost","created":"2019-05-30","cited_by_count":78},{"id":"1603.08675","title":"Quantum Recommendation Systems","created":"2016-03-29","cited_by_count":70},{"id":"1802.04020","title":"Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning","created":"2018-02-12","cited_by_count":66},{"id":"1709.04570","title":"Learning Unknown Markov Decision Processes: A Thompson Sampling Approach","created":"2017-09-14","cited_by_count":65},{"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":"1812.03584","title":"q-means: A quantum algorithm for unsupervised machine learning","created":"2018-12-10","cited_by_count":55},{"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":"2008.12776","title":"Efficiently Solving MDPs with Stochastic Mirror Descent","created":"2020-08-28","cited_by_count":53},{"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":"2007.11849","title":"Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation","created":"2020-07-23","cited_by_count":48},{"id":"2103.01312","title":"UCB Momentum Q-learning: Correcting the bias without forgetting","created":"2021-03-01","cited_by_count":46},{"id":"1906.05110","title":"Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function","created":"2019-06-12","cited_by_count":44},{"id":"2010.00587","title":"Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs","created":"2020-10-01","cited_by_count":42},{"id":"1905.11527","title":"Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies","created":"2019-05-27","cited_by_count":39},{"id":"1802.09025","title":"Online Learning of Quantum States","created":"2018-02-25","cited_by_count":37},{"id":"2106.07046","title":"Towards Tight Bounds on the Sample Complexity of Average-reward MDPs","created":"2021-06-13","cited_by_count":33},{"id":"2205.05800","title":"Stochastic first-order methods for average-reward Markov decision processes","created":"2022-05-11","cited_by_count":32},{"id":"2212.00603","title":"Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP","created":"2022-12-01","cited_by_count":29},{"id":"2306.16394","title":"Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes","created":"2023-06-28","cited_by_count":29},{"id":"2006.03864","title":"Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity","created":"2020-06-06","cited_by_count":28},{"id":"2112.08451","title":"Quantum Algorithms for Reinforcement Learning with a Generative Model","created":"2021-12-15","cited_by_count":24},{"id":"2206.04741","title":"Quantum Policy Iteration via Amplitude Estimation and Grover Search -- Towards Quantum Advantage for Reinforcement Learning","created":"2022-06-09","cited_by_count":21},{"id":"1808.01813","title":"Regret Bounds for Reinforcement Learning via Markov Chain Concentration","created":"2018-08-06","cited_by_count":19},{"id":"2002.05138","title":"Regret Bounds for Discounted MDPs","created":"2020-02-12","cited_by_count":19},{"id":"2203.01889","title":"Quantum Reinforcement Learning via Policy Iteration","created":"2022-03-03","cited_by_count":19},{"id":"2205.14988","title":"Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets","created":"2022-05-30","cited_by_count":19},{"id":"2007.05456","title":"Improved Analysis of UCRL2 with Empirical Bernstein Inequality","created":"2020-07-10","cited_by_count":18},{"id":"1302.2550","title":"Online Regret Bounds for Undiscounted Continuous Reinforcement Learning","created":"2013-02-11","cited_by_count":17},{"id":"2111.09787","title":"Near-Optimal Quantum Algorithms for Multivariate Mean Estimation","created":"2021-11-18","cited_by_count":16},{"id":"2108.12172","title":"Quantum Sub-Gaussian Mean Estimator","created":"2021-08-27","cited_by_count":15},{"id":"2212.09328","title":"Quantum policy gradient algorithms","created":"2022-12-19","cited_by_count":15},{"id":"2310.08833","title":"Optimal Sample Complexity for Average Reward Markov Decision Processes","created":"2023-10-13","cited_by_count":15},{"id":"2310.05373","title":"Quantum Bayesian Optimization","created":"2023-10-09","cited_by_count":12},{"id":"1704.01869","title":"Randomized Linear Programming Solves the Discounted Markov Decision Problem In Nearly-Linear (Sometimes Sublinear) Running Time","created":"2017-04-06","cited_by_count":11},{"id":"2110.13086","title":"Quantum Algorithms and Lower Bounds for Linear Regression with Norm Constraints","created":"2021-10-25","cited_by_count":11},{"id":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9},{"id":"2407.13743","title":"Optimistic Q-learning for average reward and episodic reinforcement learning","created":"2024-07-18","cited_by_count":9},{"id":"1301.2158","title":"Artificial Intelligence Framework for Simulating Clinical Decision-Making: A Markov Decision Process Approach","created":"2013-01-10","cited_by_count":8},{"id":"2208.07544","title":"Mean estimation when you have the source code; or, quantum Monte Carlo methods","created":"2022-08-16","cited_by_count":6},{"id":"2302.08617","title":"Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning","created":"2023-02-16","cited_by_count":6},{"id":"2308.09701","title":"Do you know what q-means?","created":"2023-08-18","cited_by_count":6},{"id":"2311.13469","title":"Span-Based Optimal Sample Complexity for Average Reward MDPs","created":"2023-11-22","cited_by_count":5},{"id":"2310.11684","title":"Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes","created":"2023-10-18","cited_by_count":3},{"id":"2507.04438","title":"Quantum Algorithms for Bandits with Knapsacks with Improved Regret and Time Complexities","created":"2025-07-06","cited_by_count":2}],"next_cursor":null}