{"list":"other","total":63,"rows":[{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"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":"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":"1806.02450","title":"A Finite Time Analysis of Temporal Difference Learning With Linear Function Approximation","created":"2018-06-06","cited_by_count":229},{"id":"1810.12429","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation","created":"2018-10-29","cited_by_count":227},{"id":"1901.00137","title":"A Theoretical Analysis of Deep Q-Learning","created":"2019-01-01","cited_by_count":215},{"id":"1906.02736","title":"DeepMDP: Learning Continuous Latent Space Models for Representation Learning","created":"2019-06-06","cited_by_count":207},{"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":"1911.09291","title":"Scalable methods for computing state similarity in deterministic Markov Decision Processes","created":"2019-11-21","cited_by_count":133},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129},{"id":"1911.06854","title":"Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning","created":"2019-11-15","cited_by_count":121},{"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":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89},{"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":"2007.11771","title":"Batch Policy Learning in Average Reward Markov Decision Processes","created":"2020-07-23","cited_by_count":69},{"id":"1701.04113","title":"Near Optimal Behavior via Approximate State Abstraction","created":"2017-01-15","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":"1809.09953","title":"Deep Neural Networks for Estimation and Inference","created":"2018-09-26","cited_by_count":62},{"id":"2001.10742","title":"Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning","created":"2020-01-29","cited_by_count":60},{"id":"1910.07186","title":"Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation","created":"2019-10-16","cited_by_count":48},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","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":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40},{"id":"2009.00148","title":"Design and Analysis of Switchback Experiments","created":"2020-08-31","cited_by_count":38},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38},{"id":"1809.04506","title":"Combined Reinforcement Learning via Abstract Representations","created":"2018-09-12","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":"1806.01347","title":"Importance Sampling Policy Evaluation with an Estimated Behavior Policy","created":"2018-06-04","cited_by_count":34},{"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":"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":"2203.00397","title":"A Theory of Abstraction in Reinforcement Learning","created":"2022-03-01","cited_by_count":27},{"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":"2207.05837","title":"Learning Bellman Complete Representations for Offline Policy Evaluation","created":"2022-07-12","cited_by_count":17},{"id":"2209.00197","title":"Switchback Experiments under Geometric Mixing","created":"2022-09-01","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":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16},{"id":"2111.04219","title":"Rate-Optimal Cluster-Randomized Designs for Spatial Interference","created":"2021-11-08","cited_by_count":14},{"id":"2406.06768","title":"Data-Driven Switchback Experiments: Theoretical Tradeoffs and Empirical Bayes Designs","created":"2024-06-10","cited_by_count":12},{"id":"2105.01136","title":"Learning Good State and Action Representations via Tensor Decomposition","created":"2021-05-03","cited_by_count":7},{"id":"2212.07486","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","created":"2022-12-14","cited_by_count":7},{"id":"2303.14281","title":"Sequential Knockoffs for Variable Selection in Reinforcement Learning","created":"2023-03-24","cited_by_count":7},{"id":"1703.03454","title":"Sample Efficient Feature Selection for Factored MDPs","created":"2017-03-09","cited_by_count":5},{"id":"2208.13871","title":"Confounder Selection: Objectives and Approaches","created":"2022-08-29","cited_by_count":4},{"id":"2310.18409","title":"State-Action Similarity-Based Representations for Off-Policy Evaluation","created":"2023-10-27","cited_by_count":4},{"id":"1704.07531","title":"Sufficient Markov Decision Processes with Alternating Deep Neural Networks","created":"2017-04-25","cited_by_count":3},{"id":"1405.5239","title":"Sequential Advantage Selection for Optimal Treatment Regimes","created":"2014-05-20","cited_by_count":2},{"id":"2309.06053","title":"Confounder selection via iterative graph expansion","created":"2023-09-12","cited_by_count":2},{"id":"1309.4054","title":"Data-driven Algorithms for Dimension Reduction in Causal Inference","created":"2013-09-16","cited_by_count":1}],"next_cursor":null}