{"list":"other","total":51,"rows":[{"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":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1807.03765","title":"Is Q-learning Provably Efficient?","created":"2018-07-10","cited_by_count":487},{"id":"1805.11074","title":"Reward Constrained Policy Optimization","created":"2018-05-28","cited_by_count":417},{"id":"1705.08551","title":"Safe Model-based Reinforcement Learning with Stability Guarantees","created":"2017-05-23","cited_by_count":366},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"2007.03964","title":"Responsive Safety in Reinforcement Learning by PID Lagrangian Methods","created":"2020-07-08","cited_by_count":316},{"id":"1805.07708","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","created":"2018-05-20","cited_by_count":297},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"1906.04733","title":"DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections","created":"2019-06-10","cited_by_count":254},{"id":"1903.08738","title":"Batch Policy Learning under Constraints","created":"2019-03-20","cited_by_count":244},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"2012.08507","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2020-12-15","cited_by_count":200},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"id":"1712.06924","title":"Safe Policy Improvement with Baseline Bootstrapping","created":"2017-12-19","cited_by_count":144},{"id":"1802.03493","title":"More Robust Doubly Robust Off-policy Evaluation","created":"2018-02-10","cited_by_count":141},{"id":"2003.00534","title":"Provably Efficient Safe Exploration via Primal-Dual Policy Optimization","created":"2020-03-01","cited_by_count":134},{"id":"2002.09072","title":"GenDICE: Generalized Offline Estimation of Stationary Values","created":"2020-02-21","cited_by_count":122},{"id":"1911.06854","title":"Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning","created":"2019-11-15","cited_by_count":121},{"id":"2002.09516","title":"Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation","created":"2020-02-21","cited_by_count":120},{"id":"2010.14497","title":"Conservative Safety Critics for Exploration","created":"2020-10-27","cited_by_count":113},{"id":"1611.01929","title":"Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning","created":"2016-11-07","cited_by_count":106},{"id":"1908.05814","title":"Linear Stochastic Bandits Under Safety Constraints","created":"2019-08-16","cited_by_count":90},{"id":"2006.12136","title":"Safe Reinforcement Learning via Curriculum Induction","created":"2020-06-22","cited_by_count":74},{"id":"2001.11113","title":"GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values","created":"2020-01-29","cited_by_count":70},{"id":"2006.10185","title":"Stochastic Bandits with Linear Constraints","created":"2020-06-17","cited_by_count":68},{"id":"2010.11652","title":"CoinDICE: Off-Policy Confidence Interval Estimation","created":"2020-10-22","cited_by_count":64},{"id":"1602.04282","title":"Conservative Bandits","created":"2016-02-13","cited_by_count":59},{"id":"1611.06426","title":"Conservative Contextual Linear Bandits","created":"2016-11-19","cited_by_count":57},{"id":"1502.04147","title":"Bayesian Incentive-Compatible Bandit Exploration","created":"2015-02-13","cited_by_count":53},{"id":"1607.03842","title":"Safe Policy Improvement by Minimizing Robust Baseline Regret","created":"2016-07-13","cited_by_count":53},{"id":"1602.04951","title":"Q($\\lambda$) with Off-Policy Corrections","created":"2016-02-16","cited_by_count":48},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43},{"id":"1910.06508","title":"Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling","created":"2019-10-15","cited_by_count":37},{"id":"2008.06668","title":"Accountable Off-Policy Evaluation With Kernel Bellman Statistics","created":"2020-08-15","cited_by_count":36},{"id":"2007.13609","title":"Statistical Bootstrapping for Uncertainty Estimation in Off-Policy Evaluation","created":"2020-07-27","cited_by_count":28},{"id":"2002.03218","title":"Conservative Exploration in Reinforcement Learning","created":"2020-02-08","cited_by_count":20},{"id":"2002.03221","title":"Improved Algorithms for Conservative Exploration in Bandits","created":"2020-02-08","cited_by_count":16},{"id":"2103.05741","title":"Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds","created":"2021-03-09","cited_by_count":11},{"id":"2012.07341","title":"A One-Size-Fits-All Solution to Conservative Bandit Problems","created":"2020-12-14","cited_by_count":5},{"id":"1806.00892","title":"Conservative Exploration using Interleaving","created":"2018-06-03","cited_by_count":4},{"id":"1911.11337","title":"Contextual Combinatorial Conservative Bandits","created":"2019-11-26","cited_by_count":4},{"id":"2104.08615","title":"Conservative Contextual Combinatorial Cascading Bandit","created":"2021-04-17","cited_by_count":3}],"next_cursor":null}