{"total":63,"rows":[{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217,"area":"mllm"},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126,"area":"offlinerl"},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104,"area":"offlinerl"},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2312.14134","title":"Diffusion Reward: Learning Rewards via Conditional Video Diffusion","created":"2023-12-21","cited_by_count":57,"area":"diffusion"},{"id":"2211.10831","title":"Joint Embedding Predictive Architectures Focus on Slow Features","created":"2022-11-20","cited_by_count":30,"area":"wm"},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2602.02454","title":"World-Gymnast: Training Robots with Reinforcement Learning in a World Model","created":"2026-02-02","cited_by_count":27,"area":"wm"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2304.13723","title":"A Control-Centric Benchmark for Video Prediction","created":"2023-04-26","cited_by_count":25,"area":null},{"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":"2405.16907","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":22,"area":"offlinerl"},{"id":"2402.02423","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","created":"2024-02-04","cited_by_count":21,"area":"alignment"},{"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":"2211.00164","title":"Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information","created":"2022-10-31","cited_by_count":16,"area":"offlinerl"},{"id":"2511.08585","title":"Simulating the Visual World with Artificial Intelligence: A Roadmap","created":"2025-11-11","cited_by_count":15,"area":"wm"},{"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":"2212.13835","title":"Representation Learning in Deep RL via Discrete Information Bottleneck","created":"2022-12-28","cited_by_count":13,"area":null},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2211.00863","title":"Behavior Prior Representation learning for Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":12,"area":"offlinerl"},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2408.08441","title":"D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning","created":"2024-08-15","cited_by_count":12,"area":"offlinerl"},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"id":"2303.06121","title":"Ignorance is Bliss: Robust Control via Information Gating","created":"2023-03-10","cited_by_count":10,"area":null},{"id":"2310.17139","title":"Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning","created":"2023-10-26","cited_by_count":10,"area":"offlinerl"},{"id":"2302.00521","title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","created":"2023-02-01","cited_by_count":8,"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":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"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":"2507.12496","title":"FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making","created":"2025-07-15","cited_by_count":8,"area":"wm"},{"id":"2606.27326","title":"Hallucination in World Models is Predictable and Preventable","created":"2026-06-25","cited_by_count":8,"area":"wm"},{"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":"2301.12056","title":"Variational Latent Branching Model for Off-Policy Evaluation","created":"2023-01-28","cited_by_count":6,"area":null},{"id":"2306.08772","title":"Katakomba: Tools and Benchmarks for Data-Driven NetHack","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2312.02019","title":"Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models","created":"2023-12-04","cited_by_count":5,"area":"wm"},{"id":"2409.18330","title":"DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors","created":"2024-09-26","cited_by_count":5,"area":"offlinerl"},{"id":"2602.07399","title":"VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation","created":"2026-02-07","cited_by_count":5,"area":"lr"},{"id":"2311.03534","title":"PcLast: Discovering Plannable Continuous Latent States","created":"2023-11-06","cited_by_count":4,"area":null},{"id":"2412.20519","title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning","created":"2024-12-29","cited_by_count":4,"area":"offlinerl"},{"id":"2502.18955","title":"Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset","created":"2025-02-26","cited_by_count":4,"area":"offlinerl"},{"id":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2211.12774","title":"Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning","created":"2022-11-23","cited_by_count":3,"area":"wm"},{"id":"2404.14552","title":"Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs","created":"2024-04-22","cited_by_count":2,"area":"deeprl"},{"id":"2410.14957","title":"Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations","created":"2024-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2212.08131","title":"Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies","created":"2022-12-15","cited_by_count":1,"area":"offlinerl"},{"id":"2406.09486","title":"SeMOPO: Learning High-quality Model and Policy from Low-quality Offline Visual Datasets","created":"2024-06-13","cited_by_count":1,"area":"offlinerl"},{"id":"2502.19544","title":"Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data","created":"2025-02-26","cited_by_count":1,"area":"wm"},{"id":"2503.00930","title":"Behavior Preference Regression for Offline Reinforcement Learning","created":"2025-03-02","cited_by_count":1,"area":"alignment"},{"id":"2505.05701","title":"Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning","created":"2025-05-09","cited_by_count":1,"area":"offlinerl"},{"id":"2505.06482","title":"Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach","created":"2025-05-10","cited_by_count":1,"area":"offlinerl"},{"id":"2506.09172","title":"An Open-Source Software Toolkit & Benchmark Suite for the Evaluation and Adaptation of Multimodal Action Models","created":"2025-06-10","cited_by_count":1,"area":"agents"},{"id":"2510.01105","title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2605.12334","title":"Reinforcing VLAs in Task-Agnostic World Models","created":"2026-05-12","cited_by_count":1,"area":"wm"},{"id":"2406.04323","title":"ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories","created":"2024-06-06","cited_by_count":0,"area":"deeprl"},{"id":"2508.12356","title":"Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data","created":"2025-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2608.14851","title":"Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"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":"2609.35880","title":"From Static Policies to Adaptive Priors in Offline Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}