{"total":84,"rows":[{"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":"2401.16013","title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","created":"2024-01-29","cited_by_count":136,"area":"deeprl"},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2207.10422","title":"Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous Driving","created":"2022-07-21","cited_by_count":73,"area":"driving"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2306.00942","title":"Train Offline, Test Online: A Real Robot Learning Benchmark","created":"2023-06-01","cited_by_count":47,"area":null},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"2210.04688","title":"BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets","created":"2022-10-07","cited_by_count":25,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2405.19946","title":"Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf","created":"2024-05-30","cited_by_count":24,"area":null},{"id":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"area":"offlinerl"},{"id":"2206.03787","title":"Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance","created":"2022-06-08","cited_by_count":22,"area":null},{"id":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2305.15284","title":"Replicable Reinforcement Learning","created":"2023-05-24","cited_by_count":21,"area":null},{"id":"2306.06871","title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles","created":"2023-06-12","cited_by_count":20,"area":"offlinerl"},{"id":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"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":"2309.03081","title":"ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":11,"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":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","cited_by_count":9,"area":"offlinerl"},{"id":"2301.11734","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","created":"2023-01-27","cited_by_count":8,"area":"offlinerl"},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2404.12530","title":"TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents","created":"2024-04-18","cited_by_count":7,"area":"offlinerl"},{"id":"2509.08660","title":"Replicable Reinforcement Learning with Linear Function Approximation","created":"2025-09-10","cited_by_count":7,"area":"deeprl"},{"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":"2301.13019","title":"Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies","created":"2023-01-30","cited_by_count":5,"area":"offlinerl"},{"id":"2312.16248","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2507.15640","title":"Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training","created":"2025-07-21","cited_by_count":5,"area":"agents"},{"id":"2305.13804","title":"OER: Offline Experience Replay for Continual Offline Reinforcement Learning","created":"2023-05-23","cited_by_count":4,"area":"offlinerl"},{"id":"2405.18757","title":"Multi-objective Cross-task Learning via Goal-conditioned GPT-based Decision Transformers for Surgical Robot Task Automation","created":"2024-05-29","cited_by_count":4,"area":"offlinerl"},{"id":"2308.07741","title":"Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World","created":"2023-08-15","cited_by_count":3,"area":"offlinerl"},{"id":"2312.02355","title":"When is Offline Policy Selection Sample Efficient for Reinforcement Learning?","created":"2023-12-04","cited_by_count":3,"area":"offlinerl"},{"id":"2402.10820","title":"Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spaces","created":"2024-02-16","cited_by_count":3,"area":"offlinerl"},{"id":"2410.12568","title":"Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving","created":"2024-10-16","cited_by_count":3,"area":"lr"},{"id":"2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","created":"2025-06-14","cited_by_count":3,"area":"deeprl"},{"id":"2303.10180","title":"Towards Real-World Applications of Personalized Anesthesia Using Policy Constraint Q Learning for Propofol Infusion Control","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2401.11630","title":"Solving Offline Reinforcement Learning with Decision Tree Regression","created":"2024-01-21","cited_by_count":2,"area":"offlinerl"},{"id":"2403.10290","title":"Offline Goal-Conditioned Reinforcement Learning for Shape Control of Deformable Linear Objects","created":"2024-03-15","cited_by_count":2,"area":"offlinerl"},{"id":"2505.10010","title":"ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts","created":"2025-05-15","cited_by_count":2,"area":"offlinerl"},{"id":"2505.10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2306.06329","title":"HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach","created":"2023-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2310.15333","title":"Safe and Interpretable Estimation of Optimal Treatment Regimes","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2311.04397","title":"ToP-ToM: Trust-aware Robot Policy with Theory of Mind","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2402.09550","title":"Dataset Clustering for Improved Offline Policy Learning","created":"2024-02-14","cited_by_count":1,"area":"offlinerl"},{"id":"2403.19024","title":"Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards","created":"2024-03-27","cited_by_count":1,"area":"alignment"},{"id":"2404.03105","title":"Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation","created":"2024-04-03","cited_by_count":1,"area":"deeprl"},{"id":"2405.16739","title":"Oracle-Efficient Reinforcement Learning for Max Value Ensembles","created":"2024-05-27","cited_by_count":1,"area":"deeprl"},{"id":"2412.18781","title":"Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations","created":"2024-12-25","cited_by_count":1,"area":"offlinerl"},{"id":"2504.18235","title":"BiasBench: A reproducible benchmark for tuning the biases of event cameras","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2512.07342","title":"PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning","created":"2025-12-08","cited_by_count":1,"area":"diffusion"},{"id":"2601.15953","title":"Decoupling Return-to-Go for Efficient Decision Transformer","created":"2026-01-22","cited_by_count":1,"area":"offlinerl"},{"id":"2603.22892","title":"VLGOR: Visual-Language Knowledge Guided Offline Reinforcement Learning for Generalizable Agents","created":"2026-03-24","cited_by_count":1,"area":"agents"},{"id":"2604.23360","title":"Learning from Demonstration with Failure Awareness for Safe Robot Navigation","created":"2026-04-25","cited_by_count":1,"area":"offlinerl"},{"id":"2605.05123","title":"Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning","created":"2026-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2211.14827","title":"Domain Generalization for Robust Model-Based Offline Reinforcement Learning","created":"2022-11-27","cited_by_count":0,"area":"offlinerl"},{"id":"2311.01749","title":"Epidemic Decision-making System Based Federated Reinforcement Learning","created":"2023-11-03","cited_by_count":0,"area":null},{"id":"2408.00023","title":"On the Perturbed States for Transformed Input-robust Reinforcement Learning","created":"2024-07-31","cited_by_count":0,"area":"deeprl"},{"id":"2408.03807","title":"Navigating the Human Maze: Real-Time Robot Pathfinding with Generative Imitation Learning","created":"2024-08-07","cited_by_count":0,"area":"offlinerl"},{"id":"2408.04198","title":"F1tenth Autonomous Racing With Offline Reinforcement Learning Methods","created":"2024-08-08","cited_by_count":0,"area":"offlinerl"},{"id":"2408.07986","title":"Experimental evaluation of offline reinforcement learning for HVAC control in buildings","created":"2024-08-15","cited_by_count":0,"area":"offlinerl"},{"id":"2502.00601","title":"Enhancing Offline Reinforcement Learning with Curriculum Learning-Based Trajectory Valuation","created":"2025-02-02","cited_by_count":0,"area":"offlinerl"},{"id":"2502.01778","title":"GNN-DT: Graph Neural Network Enhanced Decision Transformer for Efficient Optimization in Dynamic Environments","created":"2025-02-03","cited_by_count":0,"area":"offlinerl"},{"id":"2505.16754","title":"PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning Projects","created":"2025-05-22","cited_by_count":0,"area":"offlinerl"},{"id":"2505.21536","title":"CiRL: Open-Source Environments for Reinforcement Learning in Circular Economy and Net Zero","created":"2025-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2508.02581","title":"Automated Construction of Artificial Lattice Structures with Designer Electronic States","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.16858","title":"Towards an Adaptive Social Game-Playing Robot: An Offline Reinforcement Learning-Based Framework","created":"2025-09-21","cited_by_count":0,"area":"offlinerl"},{"id":"2510.06935","title":"PyCFRL: A Python library for counterfactually fair offline reinforcement learning via sequential data preprocessing","created":"2025-10-08","cited_by_count":0,"area":"offlinerl"},{"id":"2510.13358","title":"Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control","created":"2025-10-15","cited_by_count":0,"area":"offlinerl"},{"id":"2512.20115","title":"Sample-Efficient Policy Constraint Offline Deep Reinforcement Learning based on Sample Filtering","created":"2025-12-23","cited_by_count":0,"area":"offlinerl"},{"id":"2603.03932","title":"Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control","created":"2026-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2603.12284","title":"Bayesian Conservative Policy Optimization (BCPO): A Novel Uncertainty-Calibrated Offline Reinforcement Learning with Credible Lower Bounds","created":"2026-03-06","cited_by_count":0,"area":"offlinerl"},{"id":"2603.22083","title":"A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP","created":"2026-03-23","cited_by_count":0,"area":"agents"},{"id":"2605.06104","title":"Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer","created":"2026-05-07","cited_by_count":0,"area":"offlinerl"},{"id":"2605.06564","title":"Dynamic Treatment on Networks","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.13401","title":"Trajectory-Level Data Augmentation for Offline Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2608.10050","title":"Observational Policy Ranking for SMB Financial Guidance from Multi-Action Accounting Logs","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.22284","title":"Learning from the Test: Self-Referential Differential Testing for Deep RL Agents","created":"2026-08-23","cited_by_count":0,"area":"offlinerl"},{"id":"2608.30442","title":"Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry","created":"2026-08-31","cited_by_count":0,"area":"offlinerl"},{"id":"2609.08232","title":"Routing Dense Layouts with History-Aware Offline Reinforcement Learning using LSTM","created":"2026-09-08","cited_by_count":0,"area":"offlinerl"},{"id":"2609.13730","title":"JumpStart Your Policy Learning with Lessons from 160,000 Training Runs","created":"2026-09-12","cited_by_count":0,"area":"offlinerl"},{"id":"2609.22584","title":"Augmenting PID Control with Deep Reinforcement Learning: A Hybrid Approach to the Industrial Benchmark","created":"2026-09-18","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}