{"list":"other","total":55,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"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":"1909.11875","title":"Federated Learning in Mobile Edge Networks: A Comprehensive Survey","created":"2019-09-26","cited_by_count":408},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"1912.09789","title":"A Survey on Distributed Machine Learning","created":"2019-12-20","cited_by_count":188},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1703.07608","title":"Deep Exploration via Randomized Value Functions","created":"2017-03-22","cited_by_count":156},{"id":"2004.10019","title":"Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition","created":"2020-04-21","cited_by_count":127},{"id":"1808.01394","title":"Distributed Differential Privacy via Shuffling","created":"2018-08-04","cited_by_count":115},{"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":"1904.01763","title":"Batched Multi-armed Bandits Problem","created":"2019-04-03","cited_by_count":98},{"id":"1810.00068","title":"Differentially Private Contextual Linear Bandits","created":"2018-09-28","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":"1903.02837","title":"The Privacy Blanket of the Shuffle Model","created":"2019-03-07","cited_by_count":74},{"id":"1906.02870","title":"Worst-Case Regret Bounds for Exploration via Randomized Value Functions","created":"2019-06-07","cited_by_count":57},{"id":"2009.09052","title":"Private Reinforcement Learning with PAC and Regret Guarantees","created":"2020-09-18","cited_by_count":51},{"id":"1511.08681","title":"Algorithms for Differentially Private Multi-Armed Bandits","created":"2015-11-27","cited_by_count":45},{"id":"1701.07953","title":"The Price of Differential Privacy For Online Learning","created":"2017-01-27","cited_by_count":45},{"id":"2212.06069","title":"VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation","created":"2022-12-12","cited_by_count":44},{"id":"1905.11527","title":"Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies","created":"2019-05-27","cited_by_count":39},{"id":"1905.09383","title":"An Optimal Private Stochastic-MAB Algorithm Based on an Optimal Private Stopping Rule","created":"2019-05-22","cited_by_count":37},{"id":"2007.03121","title":"Multi-Armed Bandits with Local Differential Privacy","created":"2020-07-06","cited_by_count":37},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32},{"id":"2209.02570","title":"When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits","created":"2022-09-06","cited_by_count":28},{"id":"2106.02575","title":"Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits","created":"2021-06-04","cited_by_count":25},{"id":"1701.04222","title":"Achieving Privacy in the Adversarial Multi-Armed Bandit","created":"2017-01-16","cited_by_count":24},{"id":"2106.02900","title":"Differentially Private Multi-Armed Bandits in the Shuffle Model","created":"2021-06-05","cited_by_count":24},{"id":"1311.2828","title":"Private Matchings and Allocations","created":"2013-11-12","cited_by_count":23},{"id":"2112.10599","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","created":"2021-12-20","cited_by_count":23},{"id":"2010.07778","title":"Local Differential Privacy for Regret Minimization in Reinforcement Learning","created":"2020-10-15","cited_by_count":22},{"id":"2201.07052","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","created":"2022-01-18","cited_by_count":22},{"id":"2010.12163","title":"Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration","created":"2020-10-23","cited_by_count":19},{"id":"2207.03445","title":"Differentially Private Stochastic Linear Bandits: (Almost) for Free","created":"2022-07-07","cited_by_count":19},{"id":"2112.06008","title":"Privacy Amplification via Shuffling for Linear Contextual Bandits","created":"2021-12-11","cited_by_count":17},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15},{"id":"2206.05772","title":"Distributed Differential Privacy in Multi-Armed Bandits","created":"2022-06-12","cited_by_count":14},{"id":"2110.10133","title":"Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2021-10-19","cited_by_count":13},{"id":"2210.08238","title":"Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning","created":"2022-10-15","cited_by_count":13},{"id":"2202.06435","title":"Dynamic SDN-based Radio Access Network Slicing with Deep Reinforcement Learning for URLLC and eMBB Services","created":"2022-02-13","cited_by_count":12},{"id":"2111.01570","title":"Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits","created":"2021-11-02","cited_by_count":11},{"id":"2112.01585","title":"Differentially Private Exploration in Reinforcement Learning with Linear Representation","created":"2021-12-02","cited_by_count":11},{"id":"2202.01292","title":"Improved Regret for Differentially Private Exploration in Linear MDP","created":"2022-02-02","cited_by_count":8},{"id":"2405.17796","title":"Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff","created":"2024-05-28","cited_by_count":8},{"id":"2004.07778","title":"Privacy-Preserving Policy Synthesis in Markov Decision Processes","created":"2020-04-16","cited_by_count":7},{"id":"2410.22908","title":"Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents","created":"2024-10-30","cited_by_count":6},{"id":"2206.07944","title":"Distributed Online Private Learning of Convex Nondecomposable Objectives","created":"2022-06-16","cited_by_count":4},{"id":"2306.01121","title":"Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards","created":"2023-06-01","cited_by_count":4},{"id":"1302.6974","title":"Spectrum Bandit Optimization","created":"2013-02-27","cited_by_count":3},{"id":"2310.01616","title":"Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity","created":"2023-10-02","cited_by_count":2},{"id":"1609.02305","title":"Survey of Consistent Software-Defined Network Updates","created":"2016-09-08","cited_by_count":1},{"id":"2203.10165","title":"Privacy-Preserving Reinforcement Learning Beyond Expectation","created":"2022-03-18","cited_by_count":1}],"next_cursor":null}