{"list":"other","total":61,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"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":"1610.00633","title":"Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updates","created":"2016-10-03","cited_by_count":353},{"id":"2006.01107","title":"Model-Based Reinforcement Learning with Value-Targeted Regression","created":"2020-06-01","cited_by_count":234},{"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":"1908.00261","title":"On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift","created":"2019-08-01","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":"1506.03271","title":"Explore no more: Improved high-probability regret bounds for non-stochastic bandits","created":"2015-06-10","cited_by_count":120},{"id":"1909.02769","title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs","created":"2019-09-06","cited_by_count":118},{"id":"1911.00567","title":"Frequentist Regret Bounds for Randomized Least-Squares Value Iteration","created":"2019-11-01","cited_by_count":101},{"id":"1912.01192","title":"Learning Adversarial MDPs with Bandit Feedback and Unknown Transition","created":"2019-12-03","cited_by_count":85},{"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":"1602.04741","title":"Delay and Cooperation in Nonstochastic Bandits","created":"2016-02-15","cited_by_count":71},{"id":"1807.02089","title":"Linear Bandits with Stochastic Delayed Feedback","created":"2018-07-05","cited_by_count":55},{"id":"1706.09186","title":"Stochastic Bandit Models for Delayed Conversions","created":"2017-06-28","cited_by_count":54},{"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":"2002.09869","title":"Near-optimal Regret Bounds for Stochastic Shortest Path","created":"2020-02-23","cited_by_count":50},{"id":"2006.05606","title":"Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition","created":"2020-06-10","cited_by_count":48},{"id":"2007.11849","title":"Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation","created":"2020-07-23","cited_by_count":48},{"id":"1906.00670","title":"Nonstochastic Multiarmed Bandits with Unrestricted Delays","created":"2019-06-03","cited_by_count":46},{"id":"1910.06054","title":"An Optimal Algorithm for Adversarial Bandits with Arbitrary Delays","created":"2019-10-14","cited_by_count":44},{"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":"2006.10459","title":"Stochastic bandits with arm-dependent delays","created":"2020-06-18","cited_by_count":36},{"id":"1912.03517","title":"No-Regret Exploration in Goal-Oriented Reinforcement Learning","created":"2019-12-07","cited_by_count":34},{"id":"2104.11186","title":"Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret","created":"2021-04-22","cited_by_count":34},{"id":"2106.02436","title":"Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions","created":"2021-06-04","cited_by_count":34},{"id":"1803.07067","title":"Setting up a Reinforcement Learning Task with a Real-World Robot","created":"2018-03-19","cited_by_count":33},{"id":"2012.14843","title":"Learning Adversarial Markov Decision Processes with Delayed Feedback","created":"2020-12-29","cited_by_count":33},{"id":"2106.11879","title":"Asynchronous Stochastic Optimization Robust to Arbitrary Delays","created":"2021-06-22","cited_by_count":32},{"id":"2101.11992","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","created":"2021-01-28","cited_by_count":31},{"id":"2007.01612","title":"Online learning in MDPs with linear function approximation and bandit feedback","created":"2020-07-03","cited_by_count":30},{"id":"2103.13056","title":"Minimax Regret for Stochastic Shortest Path","created":"2021-03-24","cited_by_count":30},{"id":"2010.06022","title":"Adapting to Delays and Data in Adversarial Multi-Armed Bandits","created":"2020-10-12","cited_by_count":29},{"id":"2006.11561","title":"Stochastic Shortest Path with Adversarially Changing Costs","created":"2020-06-20","cited_by_count":28},{"id":"2102.05284","title":"Finding the Stochastic Shortest Path with Low Regret: The Adversarial Cost and Unknown Transition Case","created":"2021-02-10","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":"2106.08377","title":"Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path","created":"2021-06-15","cited_by_count":23},{"id":"2110.12727","title":"Learning Stochastic Shortest Path with Linear Function Approximation","created":"2021-10-25","cited_by_count":23},{"id":"2206.14906","title":"A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback","created":"2022-06-29","cited_by_count":23},{"id":"2207.10786","title":"Delayed Feedback in Generalised Linear Bandits Revisited","created":"2022-07-21","cited_by_count":23},{"id":"2201.13172","title":"Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2022-01-31","cited_by_count":22},{"id":"2301.12942","title":"Refined Regret for Adversarial MDPs with Linear Function Approximation","created":"2023-01-30","cited_by_count":19},{"id":"2111.01589","title":"Nonstochastic Bandits and Experts with Arm-Dependent Delays","created":"2021-11-02","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":"2112.02866","title":"Nonstochastic Bandits with Composite Anonymous Feedback","created":"2021-12-06","cited_by_count":16},{"id":"2105.01593","title":"Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation","created":"2021-05-04","cited_by_count":15},{"id":"2112.09859","title":"Improved No-Regret Algorithms for Stochastic Shortest Path with Linear MDP","created":"2021-12-18","cited_by_count":14},{"id":"2202.03334","title":"Policy Optimization for Stochastic Shortest Path","created":"2022-02-07","cited_by_count":13},{"id":"2201.13170","title":"Cooperative Online Learning in Stochastic and Adversarial MDPs","created":"2022-01-31","cited_by_count":4}],"next_cursor":null}