{"total":115,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2407.13734","title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review","created":"2024-07-18","cited_by_count":98,"area":"diffusion"},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2404.06356","title":"Policy-Guided Diffusion","created":"2024-04-09","cited_by_count":41,"area":"wm"},{"id":"2410.05364","title":"Diffusion Model Predictive Control","created":"2024-10-07","cited_by_count":36,"area":"diffusion"},{"id":"2505.00779","title":"Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures","created":"2025-05-01","cited_by_count":33,"area":"wm"},{"id":"2302.11048","title":"Adversarial Model for Offline Reinforcement Learning","created":"2023-02-21","cited_by_count":31,"area":"offlinerl"},{"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":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"id":"2307.03217","title":"Quantification of Uncertainty with Adversarial Models","created":"2023-07-06","cited_by_count":28,"area":null},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2405.19673","title":"Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models","created":"2024-05-30","cited_by_count":25,"area":"diffusion"},{"id":"2510.00037","title":"RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations","created":"2025-09-26","cited_by_count":25,"area":"vla"},{"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":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","cited_by_count":22,"area":"offlinerl"},{"id":"2306.14069","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","created":"2023-06-24","cited_by_count":22,"area":"offlinerl"},{"id":"2405.16907","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":22,"area":"offlinerl"},{"id":"2302.03086","title":"DITTO: Offline Imitation Learning with World Models","created":"2023-02-06","cited_by_count":21,"area":"wm"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2310.20025","title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","created":"2023-10-30","cited_by_count":20,"area":"offlinerl"},{"id":"2311.03622","title":"TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfer","created":"2023-11-07","cited_by_count":19,"area":"wm"},{"id":"2407.01418","title":"RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing","created":"2024-07-01","cited_by_count":19,"area":null},{"id":"2303.17156","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","created":"2023-03-30","cited_by_count":18,"area":"offlinerl"},{"id":"2407.00699","title":"Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning","created":"2024-06-30","cited_by_count":17,"area":"offlinerl"},{"id":"2210.03802","title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization","created":"2022-10-07","cited_by_count":16,"area":"offlinerl"},{"id":"2307.11352","title":"Model-based Offline Reinforcement Learning with Count-based Conservatism","created":"2023-07-21","cited_by_count":16,"area":"offlinerl"},{"id":"2402.03807","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","created":"2024-02-06","cited_by_count":14,"area":"offlinerl"},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"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":"2304.04660","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","created":"2023-04-10","cited_by_count":13,"area":"offlinerl"},{"id":"2306.04875","title":"Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning","created":"2023-06-08","cited_by_count":13,"area":"diffusion"},{"id":"2306.09205","title":"Reward-Free Curricula for Training Robust World Models","created":"2023-06-15","cited_by_count":13,"area":"wm"},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2310.05422","title":"Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning","created":"2023-10-09","cited_by_count":12,"area":"offlinerl"},{"id":"2205.10629","title":"User-Interactive Offline Reinforcement Learning","created":"2022-05-21","cited_by_count":11,"area":"offlinerl"},{"id":"2410.11234","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","created":"2024-10-15","cited_by_count":11,"area":"offlinerl"},{"id":"2306.07290","title":"Value function estimation using conditional diffusion models for control","created":"2023-06-09","cited_by_count":10,"area":"diffusion"},{"id":"2405.17031","title":"Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":10,"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":"2305.07958","title":"More for Less: Safe Policy Improvement With Stronger Performance Guarantees","created":"2023-05-13","cited_by_count":9,"area":"offlinerl"},{"id":"2309.08571","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","created":"2023-09-15","cited_by_count":9,"area":"offlinerl"},{"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":"2312.03991","title":"MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator","created":"2023-12-07","cited_by_count":9,"area":"offlinerl"},{"id":"2505.16377","title":"VLM-SAFE: Vision-Language Model-Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving","created":"2025-05-22","cited_by_count":9,"area":"wm"},{"id":"2506.08460","title":"MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning","created":"2025-06-10","cited_by_count":9,"area":"offlinerl"},{"id":"2306.05859","title":"Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2306.14479","title":"Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization","created":"2023-06-26","cited_by_count":8,"area":"offlinerl"},{"id":"2402.12527","title":"The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning","created":"2024-02-19","cited_by_count":8,"area":"offlinerl"},{"id":"2405.19878","title":"Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Models","created":"2024-05-30","cited_by_count":8,"area":"wm"},{"id":"2602.02900","title":"Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning","created":"2026-02-02","cited_by_count":8,"area":"offlinerl"},{"id":"2305.03360","title":"A Survey on Offline Model-Based Reinforcement Learning","created":"2023-05-05","cited_by_count":7,"area":"offlinerl"},{"id":"2305.15260","title":"Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning","created":"2023-05-24","cited_by_count":7,"area":"wm"},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2502.02844","title":"Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning","created":"2025-02-05","cited_by_count":6,"area":null},{"id":"2303.03811","title":"Environment Transformer and Policy Optimization for Model-Based Offline Reinforcement Learning","created":"2023-03-07","cited_by_count":4,"area":"offlinerl"},{"id":"2307.06328","title":"Budgeting Counterfactual for Offline RL","created":"2023-07-12","cited_by_count":4,"area":"offlinerl"},{"id":"2309.08925","title":"DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning","created":"2023-09-16","cited_by_count":4,"area":"offlinerl"},{"id":"2310.05723","title":"Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":"offlinerl"},{"id":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4,"area":"offlinerl"},{"id":"2305.13289","title":"Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach","created":"2023-05-22","cited_by_count":3,"area":"offlinerl"},{"id":"2308.06127","title":"Learning Control Policies for Variable Objectives from Offline Data","created":"2023-08-11","cited_by_count":3,"area":"offlinerl"},{"id":"2309.02157","title":"Model-based Offline Policy Optimization with Adversarial Network","created":"2023-09-05","cited_by_count":3,"area":"offlinerl"},{"id":"2310.17245","title":"CROP: Conservative Reward for Model-based Offline Policy Optimization","created":"2023-10-26","cited_by_count":3,"area":"offlinerl"},{"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":"2401.10516","title":"Episodic Reinforcement Learning with Expanded State-reward Space","created":"2024-01-19","cited_by_count":3,"area":"deeprl"},{"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":"2406.09976","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","created":"2024-06-14","cited_by_count":3,"area":"wm"},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"id":"2410.03847","title":"Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping","created":"2024-10-04","cited_by_count":3,"area":"offlinerl"},{"id":"2505.23003","title":"Hybrid Cross-domain Robust Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2603.08118","title":"Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting","created":"2026-03-09","cited_by_count":3,"area":"offlinerl"},{"id":"2311.00094","title":"A Tractable Inference Perspective of Offline RL","created":"2023-10-31","cited_by_count":2,"area":"offlinerl"},{"id":"2404.04682","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","created":"2024-04-06","cited_by_count":2,"area":"offlinerl"},{"id":"2405.19189","title":"DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning","created":"2024-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2406.04088","title":"Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning","created":"2024-06-06","cited_by_count":2,"area":"offlinerl"},{"id":"2409.02512","title":"Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal","created":"2024-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2503.19267","title":"NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic Scenarios","created":"2025-03-25","cited_by_count":2,"area":"offlinerl"},{"id":"2503.20285","title":"Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation","created":"2025-03-26","cited_by_count":2,"area":"offlinerl"},{"id":"2504.11944","title":"VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning","created":"2025-04-16","cited_by_count":2,"area":"offlinerl"},{"id":"2505.13709","title":"Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":2,"area":"wm"},{"id":"2603.09344","title":"Robust Regularized Policy Iteration under Transition Uncertainty","created":"2026-03-10","cited_by_count":2,"area":"offlinerl"},{"id":"2604.10974","title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","created":"2026-04-13","cited_by_count":2,"area":"deeprl"},{"id":"2605.05857","title":"Offline Reinforcement Learning for Rotation Profile Control in Tokamaks","created":"2026-05-07","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":"2405.14374","title":"State-Constrained Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":1,"area":"offlinerl"},{"id":"2408.10713","title":"Offline Model-Based Reinforcement Learning with Anti-Exploration","created":"2024-08-20","cited_by_count":1,"area":"offlinerl"},{"id":"2411.04915","title":"Evaluating Robustness of Reinforcement Learning Algorithms for Autonomous Shipping","created":"2024-11-07","cited_by_count":1,"area":"deeprl"},{"id":"2501.06244","title":"Microservice Deployment in Space Computing Power Networks via Robust Reinforcement Learning","created":"2025-01-08","cited_by_count":1,"area":"deeprl"},{"id":"2502.11480","title":"Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective","created":"2025-02-17","cited_by_count":1,"area":"offlinerl"},{"id":"2505.05126","title":"Taming OOD Actions for Offline Reinforcement Learning: An Advantage-Based Approach","created":"2025-05-08","cited_by_count":1,"area":"offlinerl"},{"id":"2506.12735","title":"Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space Modeling","created":"2025-06-15","cited_by_count":1,"area":"deeprl"},{"id":"2509.05735","title":"Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies","created":"2025-09-06","cited_by_count":1,"area":"wm"},{"id":"2510.22027","title":"Online Optimization for Offline Safe Reinforcement Learning","created":"2025-10-24","cited_by_count":1,"area":"offlinerl"},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2512.06692","title":"State Diversity Matters in Offline Behavior Distillation","created":"2025-12-07","cited_by_count":1,"area":"offlinerl"}],"next_cursor":"100"}