{"list":"other","total":54,"rows":[{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371},{"id":"1412.8690","title":"Breaking the Curse of Dimensionality with Convex Neural Networks","created":"2014-12-30","cited_by_count":331},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"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":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"1609.08816","title":"Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder","created":"2016-09-28","cited_by_count":139},{"id":"1906.03393","title":"Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling","created":"2019-06-08","cited_by_count":119},{"id":"2009.10982","title":"An Introduction to Proximal Causal Learning","created":"2020-09-23","cited_by_count":95},{"id":"2006.07201","title":"Minimax Estimation of Conditional Moment Models","created":"2020-06-12","cited_by_count":83},{"id":"2007.11771","title":"Batch Policy Learning in Average Reward Markov Decision Processes","created":"2020-07-23","cited_by_count":69},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69},{"id":"2006.12484","title":"Sample-Efficient Reinforcement Learning of Undercomplete POMDPs","created":"2020-06-22","cited_by_count":66},{"id":"1611.03531","title":"Estimating Dynamic Treatment Regimes in Mobile Health Using V-learning","created":"2016-11-10","cited_by_count":65},{"id":"2001.04515","title":"Statistical Inference of the Value Function for Reinforcement Learning in Infinite Horizon Settings","created":"2020-01-13","cited_by_count":65},{"id":"1902.00089","title":"Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving","created":"2019-01-29","cited_by_count":59},{"id":"2011.08411","title":"Semiparametric proximal causal inference","created":"2020-11-17","cited_by_count":59},{"id":"2002.04518","title":"Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning","created":"2020-02-11","cited_by_count":57},{"id":"1912.13088","title":"Off-Policy Estimation of Long-Term Average Outcomes with Applications to Mobile Health","created":"2019-12-30","cited_by_count":42},{"id":"2007.13893","title":"Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders","created":"2020-07-27","cited_by_count":41},{"id":"2110.15332","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","created":"2021-10-28","cited_by_count":41},{"id":"2208.06267","title":"Causal Imitation Learning with Unobserved Confounders","created":"2022-08-12","cited_by_count":41},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40},{"id":"1905.10506","title":"A Kernel Loss for Solving the Bellman Equation","created":"2019-05-25","cited_by_count":37},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36},{"id":"2202.09667","title":"Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning","created":"2022-02-19","cited_by_count":34},{"id":"2201.06169","title":"On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation","created":"2022-01-17","cited_by_count":33},{"id":"1501.06195","title":"Randomized sketches for kernels: Fast and optimal non-parametric regression","created":"2015-01-25","cited_by_count":31},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31},{"id":"2110.10719","title":"Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning","created":"2021-10-20","cited_by_count":26},{"id":"2205.13589","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","created":"2022-05-26","cited_by_count":26},{"id":"2002.04014","title":"Statistically Efficient Off-Policy Policy Gradients","created":"2020-02-10","cited_by_count":25},{"id":"1911.09260","title":"A semiparametric instrumental variable approach to optimal treatment regimes under endogeneity","created":"2019-11-21","cited_by_count":22},{"id":"2105.01187","title":"Proximal Learning for Individualized Treatment Regimes Under Unmeasured Confounding","created":"2021-05-03","cited_by_count":21},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20},{"id":"2209.08666","title":"Offline Reinforcement Learning with Instrumental Variables in Confounded Markov Decision Processes","created":"2022-09-18","cited_by_count":19},{"id":"2209.10064","title":"Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models","created":"2022-09-21","cited_by_count":18},{"id":"2204.09787","title":"Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency","created":"2022-04-20","cited_by_count":16},{"id":"1912.02793","title":"Sensitivity analysis via the proportion of unmeasured confounding","created":"2019-12-05","cited_by_count":13},{"id":"2204.00956","title":"Model-Free and Model-Based Policy Evaluation when Causality is Uncertain","created":"2022-04-02","cited_by_count":12},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7},{"id":"2305.17083","title":"A Policy Gradient Method for Confounded POMDPs","created":"2023-05-26","cited_by_count":6},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6},{"id":"2111.08885","title":"Jump Interval-Learning for Individualized Decision Making","created":"2021-11-17","cited_by_count":5},{"id":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5},{"id":"2309.13458","title":"Policy Learning for Individualized Treatment Regimes on Infinite Time Horizon","created":"2023-09-23","cited_by_count":2}],"next_cursor":null}