{"list":"other","total":51,"rows":[{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1907.05388","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation","created":"2019-07-11","cited_by_count":520},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1412.8690","title":"Breaking the Curse of Dimensionality with Convex Neural Networks","created":"2014-12-30","cited_by_count":331},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269},{"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":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"1810.08033","title":"Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality","created":"2018-10-18","cited_by_count":162},{"id":"1901.09036","title":"Orthogonal Statistical Learning","created":"2019-01-25","cited_by_count":151},{"id":"1910.12809","title":"Minimax Weight and Q-Function Learning for Off-Policy Evaluation","created":"2019-10-28","cited_by_count":150},{"id":"2010.11895","title":"What are the Statistical Limits of Offline RL with Linear Function Approximation?","created":"2020-10-22","cited_by_count":136},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123},{"id":"1911.06854","title":"Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning","created":"2019-11-15","cited_by_count":121},{"id":"1908.08526","title":"Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes","created":"2019-08-22","cited_by_count":119},{"id":"2008.04990","title":"Batch Value-function Approximation with Only Realizability","created":"2020-08-11","cited_by_count":104},{"id":"1503.04269","title":"An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning","created":"2015-03-14","cited_by_count":103},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83},{"id":"1909.05850","title":"Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning","created":"2019-09-12","cited_by_count":75},{"id":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71},{"id":"2107.11003","title":"Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings","created":"2021-07-23","cited_by_count":68},{"id":"2102.02981","title":"Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency","created":"2021-02-05","cited_by_count":56},{"id":"1702.07121","title":"Consistent On-Line Off-Policy Evaluation","created":"2017-02-23","cited_by_count":51},{"id":"1901.09455","title":"Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift","created":"2019-01-27","cited_by_count":47},{"id":"2006.13169","title":"Experience Replay with Likelihood-free Importance Weights","created":"2020-06-23","cited_by_count":42},{"id":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40},{"id":"1405.2878","title":"Approximate Policy Iteration Schemes: A Comparison","created":"2014-05-12","cited_by_count":39},{"id":"1905.10506","title":"A Kernel Loss for Solving the Bellman Equation","created":"2019-05-25","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":"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":"2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","created":"2021-04-28","cited_by_count":26},{"id":"2011.01075","title":"A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting","created":"2020-11-02","cited_by_count":25},{"id":"1506.02582","title":"On Convergence of Emphatic Temporal-Difference Learning","created":"2015-06-08","cited_by_count":21},{"id":"2207.05837","title":"Learning Bellman Complete Representations for Offline Policy Evaluation","created":"2022-07-12","cited_by_count":17},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17},{"id":"1507.01569","title":"Emphatic Temporal-Difference Learning","created":"2015-07-06","cited_by_count":16},{"id":"2103.02084","title":"Minimax Model Learning","created":"2021-03-02","cited_by_count":16},{"id":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16},{"id":"2401.09681","title":"Harnessing Density Ratios for Online Reinforcement Learning","created":"2024-01-18","cited_by_count":15},{"id":"2501.19254","title":"Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set","created":"2025-01-31","cited_by_count":12},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10},{"id":"2302.02392","title":"Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage","created":"2023-02-05","cited_by_count":10},{"id":"1704.04463","title":"On Generalized Bellman Equations and Temporal-Difference Learning","created":"2017-04-14","cited_by_count":8},{"id":"2501.06926","title":"Semiparametric Double Reinforcement Learning with Applications to Long-Term Causal Inference","created":"2025-01-12","cited_by_count":7},{"id":"2505.07729","title":"Nonparametric Instrumental Variable Inference with Many Weak Instruments","created":"2025-05-12","cited_by_count":5}],"next_cursor":null}