{"list":"other","total":51,"rows":[{"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":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"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":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161},{"id":"1802.08334","title":"Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification","created":"2018-02-22","cited_by_count":158},{"id":"1901.09036","title":"Orthogonal Statistical Learning","created":"2019-01-25","cited_by_count":151},{"id":"2203.06469","title":"Semiparametric doubly robust targeted double machine learning: a review","created":"2022-03-12","cited_by_count":133},{"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":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89},{"id":"1711.09602","title":"Deep Reinforcement Learning for Sepsis Treatment","created":"2017-11-27","cited_by_count":71},{"id":"1909.03739","title":"Off-Policy Evaluation in Partially Observable Environments","created":"2019-09-09","cited_by_count":66},{"id":"2003.05623","title":"Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding","created":"2020-03-12","cited_by_count":61},{"id":"1810.02894","title":"Interval Estimation of Individual-Level Causal Effects Under Unobserved Confounding","created":"2018-10-05","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":"2007.13893","title":"Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders","created":"2020-07-27","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":"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":"1811.09013","title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings","created":"2018-11-22","cited_by_count":34},{"id":"2011.11235","title":"An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare","created":"2020-11-23","cited_by_count":34},{"id":"1711.11286","title":"Sensitivity analysis for inverse probability weighting estimators via the percentile bootstrap","created":"2017-11-30","cited_by_count":33},{"id":"2102.04543","title":"Sharp Sensitivity Analysis for Inverse Propensity Weighting via Quantile Balancing","created":"2021-02-08","cited_by_count":32},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31},{"id":"2112.11449","title":"Doubly-Valid/Doubly-Sharp Sensitivity Analysis for Causal Inference with Unmeasured Confounding","created":"2021-12-21","cited_by_count":28},{"id":"2002.07285","title":"Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimation","created":"2020-02-17","cited_by_count":27},{"id":"2002.04014","title":"Statistically Efficient Off-Policy Policy Gradients","created":"2020-02-10","cited_by_count":25},{"id":"2112.13398","title":"Long Story Short: Omitted Variable Bias in Causal Machine Learning","created":"2021-12-26","cited_by_count":23},{"id":"2006.06731","title":"Bandits with Partially Observable Confounded Data","created":"2020-06-11","cited_by_count":22},{"id":"1811.09602","title":"Model-Based Reinforcement Learning for Sepsis Treatment","created":"2018-11-23","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":"2204.10022","title":"Scalable Sensitivity and Uncertainty Analysis for Causal-Effect Estimates of Continuous-Valued Interventions","created":"2022-04-21","cited_by_count":20},{"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":"1912.06292","title":"More Efficient Off-Policy Evaluation through Regularized Targeted Learning","created":"2019-12-13","cited_by_count":17},{"id":"1912.02793","title":"Sensitivity analysis via the proportion of unmeasured confounding","created":"2019-12-05","cited_by_count":13},{"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":"2206.01825","title":"Debiased Machine Learning without Sample-Splitting for Stable Estimators","created":"2022-06-03","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":"2210.04681","title":"Sensitivity Analysis for Marginal Structural Models","created":"2022-10-10","cited_by_count":10},{"id":"1908.01920","title":"Policy Evaluation with Latent Confounders via Optimal Balance","created":"2019-08-06","cited_by_count":8},{"id":"2104.08300","title":"Semiparametric sensitivity analysis: unmeasured confounding in observational studies","created":"2021-04-16","cited_by_count":8},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6},{"id":"2112.04571","title":"Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach","created":"2021-12-08","cited_by_count":6},{"id":"1712.10024","title":"Debiased Machine Learning of Set-Identified Linear Models","created":"2017-12-28","cited_by_count":5},{"id":"2007.02411","title":"Assessing External Validity Over Worst-case Subpopulations","created":"2020-07-05","cited_by_count":5},{"id":"1811.11301","title":"Calculating CVaR and bPOE for Common Probability Distributions With Application to Portfolio Optimization and Density Estimation","created":"2018-11-27","cited_by_count":4},{"id":"2110.13060","title":"Uniformly Conservative Exploration in Reinforcement Learning","created":"2021-10-25","cited_by_count":3},{"id":"2209.11383","title":"Model-assisted sensitivity analysis for treatment effects under unmeasured confounding via regularized calibrated estimation","created":"2022-09-23","cited_by_count":2}],"next_cursor":null}