{"total":34,"rows":[{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293,"area":"offlinerl"},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"area":"offlinerl"},{"id":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"area":"offlinerl"},{"id":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"area":"offlinerl"},{"id":"2102.05371","title":"Risk-Averse Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":65,"area":"offlinerl"},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"id":"2008.05533","title":"Overcoming Model Bias for Robust Offline Deep Reinforcement Learning","created":"2020-08-12","cited_by_count":43,"area":"offlinerl"},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2212.00124","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","created":"2022-11-30","cited_by_count":23,"area":"offlinerl"},{"id":"2402.07198","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","created":"2024-02-11","cited_by_count":23,"area":"offlinerl"},{"id":"2207.10295","title":"Addressing Optimism Bias in Sequence Modeling for Reinforcement Learning","created":"2022-07-21","cited_by_count":22,"area":"offlinerl"},{"id":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"id":"2402.08421","title":"Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning","created":"2024-02-13","cited_by_count":10,"area":"offlinerl"},{"id":"2306.07541","title":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","created":"2023-06-13","cited_by_count":8,"area":"offlinerl"},{"id":"2411.00465","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","created":"2024-11-01","cited_by_count":8,"area":"offlinerl"},{"id":"2509.23087","title":"Unleashing Flow Policies with Distributional Critics","created":"2025-09-27","cited_by_count":8,"area":"offlinerl"},{"id":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"id":"2012.13682","title":"POPO: Pessimistic Offline Policy Optimization","created":"2020-12-26","cited_by_count":5,"area":"offlinerl"},{"id":"2110.02304","title":"You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL","created":"2021-10-05","cited_by_count":4,"area":"offlinerl"},{"id":"2512.23694","title":"Bellman Calibration for $V$-Learning in Offline Reinforcement Learning","created":"2025-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2403.17646","title":"Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning","created":"2024-03-26","cited_by_count":2,"area":"offlinerl"},{"id":"2507.03900","title":"Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning","created":"2025-07-05","cited_by_count":2,"area":"offlinerl"},{"id":"2605.01663","title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","created":"2026-05-03","cited_by_count":2,"area":"offlinerl"},{"id":"2605.08253","title":"Path-Coupled Bellman Flows for Distributional Reinforcement Learning","created":"2026-05-07","cited_by_count":2,"area":"offlinerl"},{"id":"2208.00808","title":"A Maintenance Planning Framework using Online and Offline Deep Reinforcement Learning","created":"2022-08-01","cited_by_count":0,"area":"offlinerl"},{"id":"2501.12785","title":"On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration","created":"2025-01-22","cited_by_count":0,"area":"offlinerl"},{"id":"2502.20089","title":"RIZE: Adaptive Regularization for Imitation Learning","created":"2025-02-27","cited_by_count":0,"area":"offlinerl"},{"id":"2510.02695","title":"RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2510.03013","title":"Distributional Inverse Reinforcement Learning","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2511.11973","title":"Quantile Q-Learning: Revisiting Offline Extreme Q-Learning with Quantile Regression","created":"2025-11-15","cited_by_count":0,"area":"offlinerl"},{"id":"2601.01917","title":"Distorted Distributional Policy Evaluation for Offline Reinforcement Learning","created":"2026-01-05","cited_by_count":0,"area":"offlinerl"},{"id":"2608.16888","title":"Q-based Variational Inverse Reinforcement Learning","created":"2026-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2609.32828","title":"Retimed Bellman Flows: Escaping the Impossible Triangle of Velocity Bootstrapping","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}