{"total":96,"rows":[{"id":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457,"area":null},{"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":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"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":"2502.14819","title":"Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models","created":"2025-02-20","cited_by_count":89,"area":null},{"id":"2203.13251","title":"Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation","created":"2022-03-24","cited_by_count":78,"area":"offlinerl"},{"id":"2303.12076","title":"Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Play","created":"2023-03-21","cited_by_count":62,"area":null},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45,"area":"offlinerl"},{"id":"2210.13383","title":"Evaluating Long-Term Memory in 3D Mazes","created":"2022-10-24","cited_by_count":43,"area":null},{"id":"2305.02968","title":"Masked Trajectory Models for Prediction, Representation, and Control","created":"2023-05-04","cited_by_count":42,"area":"offlinerl"},{"id":"2310.16029","title":"Finetuning Offline World Models in the Real World","created":"2023-10-24","cited_by_count":41,"area":"wm"},{"id":"2305.16554","title":"Emergent Agentic Transformer from Chain of Hindsight Experience","created":"2023-05-26","cited_by_count":33,"area":"agents"},{"id":"2206.11403","title":"Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation","created":"2022-06-22","cited_by_count":31,"area":"wm"},{"id":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","cited_by_count":31,"area":null},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31,"area":"deeprl"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2301.02099","title":"Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping","created":"2023-01-05","cited_by_count":25,"area":null},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2210.09241","title":"Boosting Offline Reinforcement Learning via Data Rebalancing","created":"2022-10-17","cited_by_count":22,"area":"offlinerl"},{"id":"2510.00739","title":"TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning","created":"2025-10-01","cited_by_count":22,"area":"deeprl"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21,"area":"deeprl"},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2305.14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","created":"2023-05-23","cited_by_count":20,"area":"offlinerl"},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2411.19418","title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent","created":"2024-11-29","cited_by_count":20,"area":"deeprl"},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2304.13774","title":"Distance Weighted Supervised Learning for Offline Interaction Data","created":"2023-04-26","cited_by_count":18,"area":"offlinerl"},{"id":"2210.06479","title":"Real World Offline Reinforcement Learning with Realistic Data Source","created":"2022-10-12","cited_by_count":17,"area":"offlinerl"},{"id":"2211.01052","title":"Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints","created":"2022-11-02","cited_by_count":13,"area":"offlinerl"},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"area":"wm"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2305.19370","title":"Blockwise Parallel Transformer for Large Context Models","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2412.04368","title":"Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting","created":"2024-12-05","cited_by_count":12,"area":"offlinerl"},{"id":"2301.09544","title":"Learning to View: Decision Transformers for Active Object Detection","created":"2023-01-23","cited_by_count":11,"area":"offlinerl"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"},{"id":"2406.00324","title":"Do's and Don'ts: Learning Desirable Skills with Instruction Videos","created":"2024-06-01","cited_by_count":8,"area":null},{"id":"2606.27326","title":"Hallucination in World Models is Predictable and Preventable","created":"2026-06-25","cited_by_count":8,"area":"wm"},{"id":"2310.08558","title":"Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias","created":"2023-10-12","cited_by_count":7,"area":"offlinerl"},{"id":"2410.24218","title":"Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use","created":"2024-10-31","cited_by_count":7,"area":"deeprl"},{"id":"2412.05718","title":"RLZero: Direct Policy Inference from Language Without In-Domain Supervision","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2210.05158","title":"Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning","created":"2022-10-11","cited_by_count":6,"area":"offlinerl"},{"id":"2307.02752","title":"Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-07-06","cited_by_count":6,"area":"offlinerl"},{"id":"2406.02295","title":"How to Explore with Belief: State Entropy Maximization in POMDPs","created":"2024-06-04","cited_by_count":6,"area":"deeprl"},{"id":"2406.12795","title":"The Limits of Pure Exploration in POMDPs: When the Observation Entropy is Enough","created":"2024-06-18","cited_by_count":6,"area":null},{"id":"2506.07085","title":"State Entropy Regularization for Robust Reinforcement Learning","created":"2025-06-08","cited_by_count":6,"area":"deeprl"},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2510.20264","title":"Optimistic Task Inference for Behavior Foundation Models","created":"2025-10-23","cited_by_count":6,"area":"deeprl"},{"id":"2601.00898","title":"Dichotomous Diffusion Policy Optimization","created":"2025-12-31","cited_by_count":6,"area":"diffusion"},{"id":"2410.23810","title":"CALE: Continuous Arcade Learning Environment","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2210.07426","title":"Skill-Based Reinforcement Learning with Intrinsic Reward Matching","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","cited_by_count":4,"area":"offlinerl"},{"id":"2403.18539","title":"Safe and Robust Reinforcement Learning: Principles and Practice","created":"2024-03-27","cited_by_count":4,"area":"deeprl"},{"id":"2502.01366","title":"Trajectory World Models for Heterogeneous Environments","created":"2025-02-03","cited_by_count":4,"area":"wm"},{"id":"2502.08365","title":"Towards Principled Unsupervised Multi-Agent Reinforcement Learning","created":"2025-02-12","cited_by_count":4,"area":null},{"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":"2505.01336","title":"Enhancing Diversity in Parallel Agents: A Maximum State Entropy Exploration Story","created":"2025-05-02","cited_by_count":4,"area":"deeprl"},{"id":"2205.11357","title":"POLTER: Policy Trajectory Ensemble Regularization for Unsupervised Reinforcement Learning","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2311.16996","title":"Goal-conditioned Offline Planning from Curious Exploration","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2312.15965","title":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2510.18407","title":"Heterogeneous Adversarial Play in Interactive Environments","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2602.06769","title":"Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities","created":"2026-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2506.17155","title":"Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity","created":"2025-06-20","cited_by_count":2,"area":"offlinerl"},{"id":"2602.01962","title":"Zero-Shot Off-Policy Learning","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2206.09743","title":"Guided Safe Shooting: model based reinforcement learning with safety constraints","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2402.06102","title":"Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning","created":"2024-02-08","cited_by_count":1,"area":"deeprl"},{"id":"2411.09722","title":"Iterative Batch Reinforcement Learning via Safe Diversified Model-based Policy Search","created":"2024-11-14","cited_by_count":1,"area":"offlinerl"},{"id":"2502.04141","title":"Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning","created":"2025-02-06","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":"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":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"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":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"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":"2602.07730","title":"The Laplacian Keyboard: Beyond the Linear Span","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.14392","title":"WestWorld: A Knowledge-Encoded Scalable Trajectory World Model for Diverse Robotic Systems","created":"2026-03-15","cited_by_count":1,"area":"wm"},{"id":"2604.05931","title":"Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning","created":"2026-04-07","cited_by_count":1,"area":"deeprl"},{"id":"2604.25496","title":"Improving Zero-Shot Offline RL via Behavioral Task Sampling","created":"2026-04-28","cited_by_count":1,"area":"offlinerl"},{"id":"2606.01123","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","created":"2026-05-31","cited_by_count":1,"area":"alignment"},{"id":"2407.00744","title":"Disentangled Representations for Causal Cognition","created":"2024-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2506.19643","title":"Unsupervised Data Generation for Offline Reinforcement Learning: A Perspective from Model","created":"2025-06-24","cited_by_count":0,"area":"offlinerl"},{"id":"2605.13401","title":"Trajectory-Level Data Augmentation for Offline Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2605.17017","title":"When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited","created":"2026-05-16","cited_by_count":0,"area":"offlinerl"},{"id":"2610.05350","title":"Task Inference Beyond Least Squares in Behavioral Foundation Models","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.14400","title":"Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations","created":"2026-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2610.19883","title":"Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}