{"list":"other","total":55,"rows":[{"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":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","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":"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":"2012.08507","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2020-12-15","cited_by_count":200},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"1306.0686","title":"Online Learning under Delayed Feedback","created":"2013-06-04","cited_by_count":141},{"id":"2004.10019","title":"Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition","created":"2020-04-21","cited_by_count":127},{"id":"1607.00215","title":"Why is Posterior Sampling Better than Optimism for Reinforcement Learning?","created":"2016-07-01","cited_by_count":117},{"id":"2110.14555","title":"V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL","created":"2021-10-27","cited_by_count":114},{"id":"1510.08906","title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning","created":"2015-10-29","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":"1811.00164","title":"Deep Counterfactual Regret Minimization","created":"2018-11-01","cited_by_count":103},{"id":"2006.13165","title":"Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping","created":"2020-06-23","cited_by_count":102},{"id":"1910.10597","title":"Sample Complexity of Reinforcement Learning using Linearly Combined Model Ensembles","created":"2019-10-23","cited_by_count":100},{"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":"1912.01192","title":"Learning Adversarial MDPs with Bandit Feedback and Unknown Transition","created":"2019-12-03","cited_by_count":85},{"id":"1811.03056","title":"Policy Certificates: Towards Accountable Reinforcement Learning","created":"2018-11-07","cited_by_count":81},{"id":"1602.04741","title":"Delay and Cooperation in Nonstochastic Bandits","created":"2016-02-15","cited_by_count":71},{"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":"2006.09118","title":"$Q$-learning with Logarithmic Regret","created":"2020-06-16","cited_by_count":60},{"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":"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":"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":"1803.01626","title":"Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs","created":"2018-03-05","cited_by_count":43},{"id":"2010.00587","title":"Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs","created":"2020-10-01","cited_by_count":42},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42},{"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":"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":"2002.12174","title":"Optimistic Exploration even with a Pessimistic Initialisation","created":"2020-02-26","cited_by_count":25},{"id":"2010.08920","title":"Average-reward model-free reinforcement learning: a systematic review and literature mapping","created":"2020-10-18","cited_by_count":22},{"id":"2201.13172","title":"Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback","created":"2022-01-31","cited_by_count":22},{"id":"1605.07416","title":"Refined Lower Bounds for Adversarial Bandits","created":"2016-05-24","cited_by_count":20},{"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":"1308.4828","title":"The Sample-Complexity of General Reinforcement Learning","created":"2013-08-22","cited_by_count":18},{"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":"1807.02373","title":"Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes","created":"2018-07-06","cited_by_count":14},{"id":"2006.11911","title":"Towards Tractable Optimism in Model-Based Reinforcement Learning","created":"2020-06-21","cited_by_count":11},{"id":"1302.1611","title":"Bounded regret in stochastic multi-armed bandits","created":"2013-02-06","cited_by_count":10},{"id":"1902.07286","title":"Online Learning with Continuous Variations: Dynamic Regret and Reductions","created":"2019-02-19","cited_by_count":10},{"id":"1911.05873","title":"A Reduction from Reinforcement Learning to No-Regret Online Learning","created":"2019-11-14","cited_by_count":10},{"id":"2002.03585","title":"On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning","created":"2020-02-10","cited_by_count":10},{"id":"2007.10916","title":"On the Convergence of Reinforcement Learning with Monte Carlo Exploring Starts","created":"2020-07-21","cited_by_count":9},{"id":"2201.12224","title":"Learning Stationary Nash Equilibrium Policies in $n$-Player Stochastic Games with Independent Chains","created":"2022-01-28","cited_by_count":7},{"id":"1802.09184","title":"Variance Reduction Methods for Sublinear Reinforcement Learning","created":"2018-02-26","cited_by_count":6}],"next_cursor":null}