{"list":"other","total":65,"rows":[{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"id":"1610.09512","title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","created":"2016-10-29","cited_by_count":292},{"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":"2003.00153","title":"Learning Near Optimal Policies with Low Inherent Bellman Error","created":"2020-02-29","cited_by_count":181},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164},{"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":"1802.03493","title":"More Robust Doubly Robust Off-policy Evaluation","created":"2018-02-10","cited_by_count":141},{"id":"1609.08816","title":"Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder","created":"2016-09-28","cited_by_count":139},{"id":"2002.09516","title":"Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation","created":"2020-02-21","cited_by_count":120},{"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":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100},{"id":"1905.12495","title":"Deep Generalized Method of Moments for Instrumental Variable Analysis","created":"2019-05-29","cited_by_count":88},{"id":"2001.09254","title":"Improper Learning for Non-Stochastic Control","created":"2020-01-25","cited_by_count":83},{"id":"2006.07201","title":"Minimax Estimation of Conditional Moment Models","created":"2020-06-12","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":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70},{"id":"2007.11771","title":"Batch Policy Learning in Average Reward Markov Decision Processes","created":"2020-07-23","cited_by_count":69},{"id":"1909.03739","title":"Off-Policy Evaluation in Partially Observable Environments","created":"2019-09-09","cited_by_count":66},{"id":"2006.12484","title":"Sample-Efficient Reinforcement Learning of Undercomplete POMDPs","created":"2020-06-22","cited_by_count":66},{"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":"1801.02143","title":"Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction","created":"2018-01-07","cited_by_count":61},{"id":"2003.05623","title":"Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding","created":"2020-03-12","cited_by_count":61},{"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":"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":"1602.07764","title":"Reinforcement Learning of POMDPs using Spectral Methods","created":"2016-02-25","cited_by_count":52},{"id":"2103.14029","title":"Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach","created":"2021-03-25","cited_by_count":44},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43},{"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":"2006.12311","title":"Provably Efficient Causal Reinforcement Learning with Confounded Observational Data","created":"2020-06-22","cited_by_count":40},{"id":"1605.08062","title":"A PAC RL Algorithm for Episodic POMDPs","created":"2016-05-25","cited_by_count":37},{"id":"1905.10506","title":"A Kernel Loss for Solving the Bellman Equation","created":"2019-05-25","cited_by_count":37},{"id":"1808.04945","title":"A confounding bridge approach for double negative control inference on causal effects","created":"2018-08-15","cited_by_count":36},{"id":"2001.04032","title":"POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning","created":"2020-01-13","cited_by_count":36},{"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":"2101.00009","title":"Adversarial Estimation of Riesz Representers","created":"2020-12-30","cited_by_count":35},{"id":"2102.09907","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","created":"2021-02-19","cited_by_count":35},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35},{"id":"1712.00038","title":"Augmented Minimax Linear Estimation","created":"2017-11-30","cited_by_count":33},{"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":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31},{"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":"2107.08828","title":"Reinforcement Learning for Education: Opportunities and Challenges","created":"2021-07-15","cited_by_count":25},{"id":"2201.04735","title":"Planning in Observable POMDPs in Quasipolynomial Time","created":"2022-01-12","cited_by_count":25},{"id":"2011.04019","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","created":"2020-11-08","cited_by_count":24},{"id":"2110.12343","title":"Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability","created":"2021-10-24","cited_by_count":24},{"id":"2010.07452","title":"Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes","created":"2020-10-15","cited_by_count":23},{"id":"2109.10502","title":"A Spectral Approach to Off-Policy Evaluation for POMDPs","created":"2021-09-22","cited_by_count":21},{"id":"1912.06292","title":"More Efficient Off-Policy Evaluation through Regularized Targeted Learning","created":"2019-12-13","cited_by_count":17},{"id":"1309.6819","title":"Hilbert Space Embeddings of Predictive State Representations","created":"2013-09-26","cited_by_count":16},{"id":"1705.09353","title":"Predictive State Recurrent Neural Networks","created":"2017-05-25","cited_by_count":14},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10},{"id":"2005.13001","title":"Latent-state models for precision medicine","created":"2020-05-26","cited_by_count":6}],"next_cursor":null}