{"total":51,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40,"area":"offlinerl"},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36,"area":"offlinerl"},{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31,"area":null},{"id":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"id":"2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","created":"2021-04-28","cited_by_count":26,"area":null},{"id":"2310.17966","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","created":"2023-10-27","cited_by_count":26,"area":"offlinerl"},{"id":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25,"area":null},{"id":"2011.04019","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","created":"2020-11-08","cited_by_count":24,"area":"offlinerl"},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","cited_by_count":18,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"area":null},{"id":"2207.05219","title":"Grounding Aleatoric Uncertainty for Unsupervised Environment Design","created":"2022-07-11","cited_by_count":16,"area":null},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14,"area":null},{"id":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2405.21043","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9,"area":null},{"id":"2306.13284","title":"Correcting discount-factor mismatch in on-policy policy gradient methods","created":"2023-06-23","cited_by_count":9,"area":null},{"id":"2212.07486","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","created":"2022-12-14","cited_by_count":7,"area":null},{"id":"2308.01170","title":"Revisiting a Design Choice in Gradient Temporal Difference Learning","created":"2023-08-02","cited_by_count":7,"area":null},{"id":"2410.04108","title":"On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning","created":"2024-10-05","cited_by_count":6,"area":"offlinerl"},{"id":"2410.15698","title":"Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces","created":"2024-10-21","cited_by_count":6,"area":"offlinerl"},{"id":"2107.05405","title":"Learning Expected Emphatic Traces for Deep RL","created":"2021-07-12","cited_by_count":5,"area":null},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","created":"2021-11-16","cited_by_count":5,"area":null},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2206.02000","title":"Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning","created":"2022-06-04","cited_by_count":3,"area":"offlinerl"},{"id":"2211.15355","title":"Causal Deep Reinforcement Learning Using Observational Data","created":"2022-11-28","cited_by_count":3,"area":null},{"id":"2211.16078","title":"Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning","created":"2022-11-29","cited_by_count":2,"area":"offlinerl"},{"id":"2301.13348","title":"A Reinforcement Learning Framework for Dynamic Mediation Analysis","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2307.15892","title":"A new Gradient TD Algorithm with only One Step-size: Convergence Rate Analysis using $L$-$\\lambda$ Smoothness","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2402.12034","title":"When Do Off-Policy and On-Policy Policy Gradient Methods Align?","created":"2024-02-19","cited_by_count":2,"area":"deeprl"},{"id":"2503.02125","title":"Average-DICE: Stationary Distribution Correction by Regression","created":"2025-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2107.02711","title":"A Unified Off-Policy Evaluation Approach for General Value Function","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2203.10172","title":"Importance Sampling Placement in Off-Policy Temporal-Difference Methods","created":"2022-03-18","cited_by_count":1,"area":null},{"id":"2311.14885","title":"Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning","created":"2023-11-25","cited_by_count":1,"area":"offlinerl"},{"id":"2512.15439","title":"Double Horizon Model-Based Policy Optimization","created":"2025-12-17","cited_by_count":1,"area":"deeprl"},{"id":"2103.10752","title":"Forward and Backward Bellman equations improve the efficiency of EM algorithm for DEC-POMDP","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2403.01605","title":"Towards Provable Log Density Policy Gradient","created":"2024-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2412.06486","title":"SimuDICE: Offline Policy Optimization Through World Model Updates and DICE Estimation","created":"2024-12-09","cited_by_count":0,"area":"wm"},{"id":"2604.18972","title":"Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.28855","title":"Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.25923","title":"$\\text{DT}^2$: Decision-Targeted Digital Twins","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.24858","title":"Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning","created":"2026-08-25","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}