{"list":"other","total":56,"rows":[{"id":"1705.08821","title":"Causal Effect Inference with Deep Latent-Variable Models","created":"2017-05-24","cited_by_count":410},{"id":"1511.03722","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","created":"2015-11-11","cited_by_count":339},{"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":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"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":"2002.09072","title":"GenDICE: Generalized Offline Estimation of Stationary Values","created":"2020-02-21","cited_by_count":122},{"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":"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":"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":"2010.11652","title":"CoinDICE: Off-Policy Confidence Interval Estimation","created":"2020-10-22","cited_by_count":64},{"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":"1602.07764","title":"Reinforcement Learning of POMDPs using Spectral Methods","created":"2016-02-25","cited_by_count":52},{"id":"1702.07121","title":"Consistent On-Line Off-Policy Evaluation","created":"2017-02-23","cited_by_count":51},{"id":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"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":"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":"2006.12311","title":"Provably Efficient Causal Reinforcement Learning with Confounded Observational Data","created":"2020-06-22","cited_by_count":40},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40},{"id":"2106.03907","title":"Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation","created":"2021-06-07","cited_by_count":40},{"id":"1605.08062","title":"A PAC RL Algorithm for Episodic POMDPs","created":"2016-05-25","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":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","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":"2102.09907","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","created":"2021-02-19","cited_by_count":35},{"id":"1802.10264","title":"Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods","created":"2018-02-28","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":"2002.01751","title":"Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making","created":"2020-02-05","cited_by_count":30},{"id":"2202.01562","title":"Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model","created":"2022-02-03","cited_by_count":30},{"id":"1606.00119","title":"Contextual Bandits with Latent Confounders: An NMF Approach","created":"2016-06-01","cited_by_count":26},{"id":"1906.04328","title":"Importance Resampling for Off-policy Prediction","created":"2019-06-11","cited_by_count":26},{"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":"1611.09925","title":"Bounded, efficient and multiply robust estimation of average treatment effects using instrumental variables","created":"2016-11-29","cited_by_count":23},{"id":"1911.09260","title":"A semiparametric instrumental variable approach to optimal treatment regimes under endogeneity","created":"2019-11-21","cited_by_count":22},{"id":"2109.10502","title":"A Spectral Approach to Off-Policy Evaluation for POMDPs","created":"2021-09-22","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":"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":"2010.15963","title":"Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings","created":"2020-10-29","cited_by_count":14},{"id":"2104.07822","title":"Estimating and Improving Dynamic Treatment Regimes With a Time-Varying Instrumental Variable","created":"2021-04-15","cited_by_count":13},{"id":"2103.04021","title":"Asymptotic Theory for IV-Based Reinforcement Learning with Potential Endogeneity","created":"2021-03-06","cited_by_count":8},{"id":"1406.0764","title":"Constructing Dynamic Treatment Regimes in Infinite-Horizon Settings","created":"2014-06-03","cited_by_count":4}],"next_cursor":null}