{"total":86,"rows":[{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2506.00613","title":"WorldGym: World Model as An Environment for Policy Evaluation","created":"2025-05-31","cited_by_count":64,"area":"wm"},{"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,"area":"offlinerl"},{"id":"2103.14029","title":"Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach","created":"2021-03-25","cited_by_count":44,"area":null},{"id":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41,"area":"offlinerl"},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36,"area":"offlinerl"},{"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,"area":null},{"id":"2203.13935","title":"Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps","created":"2022-03-25","cited_by_count":34,"area":"offlinerl"},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2102.09468","title":"Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimization","created":"2021-02-18","cited_by_count":31,"area":null},{"id":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"area":"offlinerl"},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"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":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2303.02569","title":"Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching","created":"2023-03-05","cited_by_count":24,"area":"offlinerl"},{"id":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"area":null},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2206.02371","title":"Markovian Interference in Experiments","created":"2022-06-06","cited_by_count":22,"area":null},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21,"area":null},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2302.09456","title":"Distributional Offline Policy Evaluation with Predictive Error Guarantees","created":"2023-02-19","cited_by_count":20,"area":"diffusion"},{"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":"2207.05837","title":"Learning Bellman Complete Representations for Offline Policy Evaluation","created":"2022-07-12","cited_by_count":17,"area":"offlinerl"},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17,"area":null},{"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,"area":null},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2210.05922","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","created":"2022-10-12","cited_by_count":14,"area":"offlinerl"},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"area":null},{"id":"2402.12570","title":"Offline Multi-task Transfer RL with Representational Penalization","created":"2024-02-19","cited_by_count":14,"area":"offlinerl"},{"id":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2311.18207","title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2208.08291","title":"Inference on Strongly Identified Functionals of Weakly Identified Functions","created":"2022-08-17","cited_by_count":12,"area":null},{"id":"2103.05741","title":"Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds","created":"2021-03-09","cited_by_count":11,"area":null},{"id":"2108.08765","title":"Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation","created":"2021-08-19","cited_by_count":11,"area":"offlinerl"},{"id":"2103.09847","title":"Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm","created":"2021-03-17","cited_by_count":10,"area":"offlinerl"},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"id":"2302.02392","title":"Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage","created":"2023-02-05","cited_by_count":10,"area":"offlinerl"},{"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":"2110.12468","title":"False Correlation Reduction for Offline Reinforcement Learning","created":"2021-10-24","cited_by_count":9,"area":"offlinerl"},{"id":"2302.06884","title":"Conservative State Value Estimation for Offline Reinforcement Learning","created":"2023-02-14","cited_by_count":9,"area":"offlinerl"},{"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,"area":null},{"id":"2302.02477","title":"Offline Learning of Closed-Loop Deep Brain Stimulation Controllers for Parkinson Disease Treatment","created":"2023-02-05","cited_by_count":8,"area":null},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"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":"2301.12056","title":"Variational Latent Branching Model for Off-Policy Evaluation","created":"2023-01-28","cited_by_count":6,"area":null},{"id":"2310.07123","title":"Off-Policy Evaluation for Human Feedback","created":"2023-10-11","cited_by_count":6,"area":"alignment"},{"id":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"id":"2106.00993","title":"On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction","created":"2021-06-02","cited_by_count":5,"area":null},{"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":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"id":"2310.18409","title":"State-Action Similarity-Based Representations for Off-Policy Evaluation","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2311.14110","title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","created":"2023-11-23","cited_by_count":4,"area":"alignment"},{"id":"2410.17538","title":"Primal-Dual Spectral Representation for Off-policy Evaluation","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2502.01366","title":"Trajectory World Models for Heterogeneous Environments","created":"2025-02-03","cited_by_count":4,"area":"wm"},{"id":"2502.19255","title":"Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective","created":"2025-02-26","cited_by_count":4,"area":"alignment"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2109.11867","title":"The $f$-Divergence Reinforcement Learning Framework","created":"2021-09-24","cited_by_count":3,"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":"2312.11551","title":"Probabilistic Offline Policy Ranking with Approximate Bayesian Computation","created":"2023-12-17","cited_by_count":3,"area":null},{"id":"2405.17708","title":"OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2405.18792","title":"Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies","created":"2024-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2110.02421","title":"Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2301.10330","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2303.11187","title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2503.02125","title":"Average-DICE: Stationary Distribution Correction by Regression","created":"2025-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2505.20781","title":"STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation","created":"2025-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2205.02976","title":"Variance Reduction based Partial Trajectory Reuse to Accelerate Policy Gradient Optimization","created":"2022-05-06","cited_by_count":1,"area":null},{"id":"2207.11161","title":"Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2208.12341","title":"Variance Reduction based Experience Replay for Policy Optimization","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.08644","title":"Semi-gradient DICE for Offline Constrained Reinforcement Learning","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2512.10042","title":"SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation","created":"2025-12-10","cited_by_count":1,"area":"deeprl"},{"id":"2110.12081","title":"Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction","created":"2021-10-22","cited_by_count":0,"area":null},{"id":"2203.16177","title":"Marginalized Operators for Off-policy Reinforcement Learning","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2410.20017","title":"Off-Policy Selection for Initiating Human-Centric Experimental Design","created":"2024-10-26","cited_by_count":0,"area":null},{"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":"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}