{"list":"other","total":95,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"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":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"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":"1503.02834","title":"Doubly Robust Policy Evaluation and Optimization","created":"2015-03-10","cited_by_count":158},{"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":"1910.03016","title":"Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?","created":"2019-10-07","cited_by_count":140},{"id":"1609.08816","title":"Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder","created":"2016-09-28","cited_by_count":139},{"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":"2203.06469","title":"Semiparametric doubly robust targeted double machine learning: a review","created":"2022-03-12","cited_by_count":133},{"id":"2002.09516","title":"Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation","created":"2020-02-21","cited_by_count":120},{"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":"1908.08526","title":"Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes","created":"2019-08-22","cited_by_count":119},{"id":"1612.01205","title":"Optimal and Adaptive Off-policy Evaluation in Contextual Bandits","created":"2016-12-04","cited_by_count":111},{"id":"2001.01866","title":"Reinforcement Learning via Fenchel-Rockafellar Duality","created":"2020-01-07","cited_by_count":100},{"id":"1907.09623","title":"Doubly robust off-policy evaluation with shrinkage","created":"2019-07-22","cited_by_count":87},{"id":"2007.03438","title":"Off-Policy Evaluation via the Regularized Lagrangian","created":"2020-07-07","cited_by_count":86},{"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":"1908.00695","title":"Deep ReLU network approximation of functions on a manifold","created":"2019-08-02","cited_by_count":74},{"id":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71},{"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":"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":"1507.00747","title":"Nonparametric methods for doubly robust estimation of continuous treatment effects","created":"2015-07-02","cited_by_count":64},{"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":"2001.10742","title":"Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning","created":"2020-01-29","cited_by_count":60},{"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":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"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":"2103.13883","title":"Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning","created":"2021-03-25","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":"2006.10460","title":"Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting","created":"2020-06-18","cited_by_count":38},{"id":"1905.10506","title":"A Kernel Loss for Solving the Bellman Equation","created":"2019-05-25","cited_by_count":37},{"id":"1910.06508","title":"Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling","created":"2019-10-15","cited_by_count":37},{"id":"2001.04032","title":"POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning","created":"2020-01-13","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":"2101.00009","title":"Adversarial Estimation of Riesz Representers","created":"2020-12-30","cited_by_count":35},{"id":"1802.08667","title":"De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers","created":"2018-02-23","cited_by_count":34},{"id":"1712.00038","title":"Augmented Minimax Linear Estimation","created":"2017-11-30","cited_by_count":33},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33},{"id":"2112.12770","title":"Optimal and instance-dependent guarantees for Markovian linear stochastic approximation","created":"2021-12-23","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":"2002.01711","title":"Dynamic Causal Effects Evaluation in A/B Testing with a Reinforcement Learning Framework","created":"2020-02-05","cited_by_count":29},{"id":"1704.00211","title":"Nonparametric causal effects based on incremental propensity score interventions","created":"2017-04-01","cited_by_count":28},{"id":"1906.03735","title":"Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning","created":"2019-06-09","cited_by_count":28},{"id":"2006.15121","title":"Learning Optimal Distributionally Robust Individualized Treatment Rules","created":"2020-06-26","cited_by_count":28},{"id":"1601.00237","title":"Assessing Time-Varying Causal Effect Moderation in Mobile Health","created":"2016-01-03","cited_by_count":27},{"id":"2110.10719","title":"Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning","created":"2021-10-20","cited_by_count":26},{"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":"2003.12659","title":"Semiparametric Inference For Causal Effects In Graphical Models With Hidden Variables","created":"2020-03-27","cited_by_count":23},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21},{"id":"1703.06180","title":"Effective Evaluation using Logged Bandit Feedback from Multiple Loggers","created":"2017-03-17","cited_by_count":20},{"id":"1702.02896","title":"Policy Learning with Observational Data","created":"2017-02-09","cited_by_count":19},{"id":"2209.08666","title":"Offline Reinforcement Learning with Instrumental Variables in Confounded Markov Decision Processes","created":"2022-09-18","cited_by_count":19},{"id":"1705.00998","title":"Minimal Dispersion Approximately Balancing Weights: Asymptotic Properties and Practical Considerations","created":"2017-05-02","cited_by_count":18},{"id":"2202.04970","title":"Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory","created":"2022-02-10","cited_by_count":18},{"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":"1606.01472","title":"Interpretable Dynamic Treatment Regimes","created":"2016-06-05","cited_by_count":17},{"id":"1912.06292","title":"More Efficient Off-Policy Evaluation through Regularized Targeted Learning","created":"2019-12-13","cited_by_count":17},{"id":"2102.10242","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","created":"2021-02-20","cited_by_count":16},{"id":"1809.03084","title":"Efficient Counterfactual Learning from Bandit Feedback","created":"2018-09-10","cited_by_count":15},{"id":"2004.10521","title":"Efficient adjustment sets in causal graphical models with hidden variables","created":"2020-04-22","cited_by_count":13},{"id":"1812.08683","title":"Robust Estimation of Causal Effects via High-Dimensional Covariate Balancing Propensity Score","created":"2018-12-20","cited_by_count":12},{"id":"2203.01707","title":"Testing Stationarity and Change Point Detection in Reinforcement Learning","created":"2022-03-03","cited_by_count":12},{"id":"1504.07715","title":"Using Decision Lists to Construct Interpretable and Parsimonious Treatment Regimes","created":"2015-04-29","cited_by_count":11},{"id":"1906.03694","title":"Balanced off-policy evaluation in general action spaces","created":"2019-06-09","cited_by_count":11},{"id":"2001.03258","title":"Personalized Policy Learning using Longitudinal Mobile Health Data","created":"2020-01-09","cited_by_count":10},{"id":"2006.03900","title":"Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies","created":"2020-06-06","cited_by_count":10},{"id":"2209.13075","title":"Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency","created":"2022-09-26","cited_by_count":10},{"id":"1407.7820","title":"On Estimation of Optimal Treatment Regimes For Maximizing t-Year Survival Probability","created":"2014-07-29","cited_by_count":9},{"id":"2006.03886","title":"Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning","created":"2020-06-06","cited_by_count":8},{"id":"2210.15543","title":"Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions","created":"2022-10-27","cited_by_count":8},{"id":"1603.06372","title":"Evaluating the Impact of Treating the Optimal Subgroup","created":"2016-03-21","cited_by_count":5},{"id":"1706.07408","title":"Data-adaptive smoothing for optimal-rate estimation of possibly non-regular parameters","created":"2017-06-22","cited_by_count":3},{"id":"1911.11043","title":"Resampling-based Confidence Intervals for Model-free Robust Inference on Optimal Treatment Regimes","created":"2019-11-25","cited_by_count":3},{"id":"1910.00641","title":"An introduction to flexible methods for policy evaluation","created":"2019-10-01","cited_by_count":2}],"next_cursor":null}