{"total":53,"rows":[{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37,"area":null},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2211.11349","title":"Data-Driven Offline Decision-Making via Invariant Representation Learning","created":"2022-11-21","cited_by_count":31,"area":null},{"id":"2112.10504","title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic","created":"2021-12-16","cited_by_count":23,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2207.08673","title":"Back to the Manifold: Recovering from Out-of-Distribution States","created":"2022-07-18","cited_by_count":20,"area":null},{"id":"2211.11802","title":"Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning","created":"2022-11-21","cited_by_count":20,"area":null},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"area":null},{"id":"2305.09648","title":"Prompt-Tuning Decision Transformer with Preference Ranking","created":"2023-05-16","cited_by_count":19,"area":null},{"id":"2405.05349","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2503.17286","title":"Offline Model-Based Optimization: Comprehensive Review","created":"2025-03-21","cited_by_count":15,"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":"2310.19308","title":"Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning","created":"2023-10-30","cited_by_count":13,"area":null},{"id":"2306.06335","title":"How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations","created":"2023-06-10","cited_by_count":10,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2311.01059","title":"Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2403.06328","title":"Distributional Successor Features Enable Zero-Shot Policy Optimization","created":"2024-03-10","cited_by_count":8,"area":null},{"id":"2311.06554","title":"PGODE: Towards High-quality System Dynamics Modeling","created":"2023-11-11","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":"2410.11711","title":"Zero-shot Model-based Reinforcement Learning using Large Language Models","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2110.11073","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2309.01807","title":"Marginalized Importance Sampling for Off-Environment Policy Evaluation","created":"2023-09-04","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2504.01766","title":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2206.08851","title":"SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments","created":"2022-06-17","cited_by_count":4,"area":null},{"id":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2106.03279","title":"Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2307.13101","title":"Contrastive Example-Based Control","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2401.01369","title":"RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems","created":"2023-12-27","cited_by_count":3,"area":null},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2303.02234","title":"Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2305.11340","title":"Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models","created":"2023-05-18","cited_by_count":2,"area":null},{"id":"2309.13508","title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","created":"2023-09-24","cited_by_count":2,"area":null},{"id":"2205.07250","title":"A cGAN Ensemble-based Uncertainty-aware Surrogate Model for Offline Model-based Optimization in Industrial Control Problems","created":"2022-05-15","cited_by_count":1,"area":null},{"id":"2409.13299","title":"OMG-RL:Offline Model-based Guided Reward Learning for Heparin Treatment","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2602.05776","title":"Cross-Domain Offline Policy Adaptation via Selective Transition Correction","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.16789","title":"Conservative Continuous-Time Treatment Optimization","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2205.13950","title":"Non-Markovian policies occupancy measures","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2304.00573","title":"Risk-Sensitive and Robust Model-Based Reinforcement Learning and Planning","created":"2023-04-02","cited_by_count":0,"area":null},{"id":"2401.00330","title":"Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions","created":"2023-12-30","cited_by_count":0,"area":null},{"id":"2405.12001","title":"Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2610.03065","title":"Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}