{"total":89,"rows":[{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395,"area":"offlinerl"},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134,"area":"offlinerl"},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2309.10150","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","created":"2023-09-18","cited_by_count":131,"area":"offlinerl"},{"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":"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":"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":"2406.14532","title":"RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold","created":"2024-06-20","cited_by_count":99,"area":"lr"},{"id":"2506.10943","title":"Self-Adapting Language Models","created":"2025-06-12","cited_by_count":84,"area":null},{"id":"2412.16145","title":"Offline Reinforcement Learning for LLM Multi-Step Reasoning","created":"2024-12-20","cited_by_count":54,"area":"lr"},{"id":"2311.05584","title":"Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations","created":"2023-11-09","cited_by_count":38,"area":null},{"id":"2506.13725","title":"CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding","created":"2025-06-16","cited_by_count":38,"area":"vla"},{"id":"2503.08007","title":"MoRE: Unlocking Scalability in Reinforcement Learning for Quadruped Vision-Language-Action Models","created":"2025-03-11","cited_by_count":27,"area":"vla"},{"id":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22,"area":null},{"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":"2407.06946","title":"Self-Recognition in Language Models","created":"2024-07-09","cited_by_count":18,"area":null},{"id":"2210.06479","title":"Real World Offline Reinforcement Learning with Realistic Data Source","created":"2022-10-12","cited_by_count":17,"area":"offlinerl"},{"id":"2212.01375","title":"Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curricula","created":"2022-12-02","cited_by_count":17,"area":"driving"},{"id":"2309.02236","title":"Distributionally Robust Model-based Reinforcement Learning with Large State Spaces","created":"2023-09-05","cited_by_count":17,"area":null},{"id":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15,"area":"offlinerl"},{"id":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2310.14196","title":"Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning","created":"2023-10-22","cited_by_count":15,"area":"offlinerl"},{"id":"2309.09408","title":"Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration","created":"2023-09-18","cited_by_count":14,"area":"offlinerl"},{"id":"2410.08048","title":"VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers","created":"2024-10-10","cited_by_count":14,"area":"lr"},{"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":"2406.17768","title":"EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data","created":"2024-06-25","cited_by_count":13,"area":"deeprl"},{"id":"2311.11423","title":"Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets","created":"2023-11-19","cited_by_count":12,"area":"offlinerl"},{"id":"2505.18098","title":"Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2411.05193","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","created":"2024-11-07","cited_by_count":10,"area":"offlinerl"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2212.04280","title":"Model-based trajectory stitching for improved behavioural cloning and its applications","created":"2022-12-08","cited_by_count":9,"area":"offlinerl"},{"id":"2410.14069","title":"Rethinking Optimal Transport in Offline Reinforcement Learning","created":"2024-10-17","cited_by_count":9,"area":"offlinerl"},{"id":"2512.02011","title":"Learning Dexterous Manipulation Skills from Imperfect Simulations","created":"2025-12-01","cited_by_count":9,"area":"deeprl"},{"id":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2310.20663","title":"Offline RL with Observation Histories: Analyzing and Improving Sample Complexity","created":"2023-10-31","cited_by_count":7,"area":"offlinerl"},{"id":"2402.02017","title":"Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning","created":"2024-02-03","cited_by_count":7,"area":"offlinerl"},{"id":"2504.18026","title":"Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization","created":"2025-04-25","cited_by_count":7,"area":"alignment"},{"id":"2305.16209","title":"C-MCTS: Safe Planning with Monte Carlo Tree Search","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2306.03857","title":"Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2409.10589","title":"Offline Reinforcement Learning for Learning to Dispatch for Job Shop Scheduling","created":"2024-09-16","cited_by_count":6,"area":"offlinerl"},{"id":"2410.03408","title":"Predictive Coding for Decision Transformer","created":"2024-10-04","cited_by_count":6,"area":"offlinerl"},{"id":"2205.13274","title":"Evaluating Multimodal Interactive Agents","created":"2022-05-26","cited_by_count":5,"area":null},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","cited_by_count":5,"area":"offlinerl"},{"id":"2312.10547","title":"Advancing RAN Slicing with Offline Reinforcement Learning","created":"2023-12-16","cited_by_count":5,"area":"offlinerl"},{"id":"2503.14259","title":"Quantization-Free Autoregressive Action Transformer","created":"2025-03-18","cited_by_count":5,"area":"offlinerl"},{"id":"2305.13078","title":"Optimality Principles in Spacecraft Neural Guidance and Control","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2503.12222","title":"Evaluation-Time Policy Switching for Offline Reinforcement Learning","created":"2025-03-15","cited_by_count":4,"area":"offlinerl"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2401.09243","title":"DiffClone: Enhanced Behaviour Cloning in Robotics with Diffusion-Driven Policy Learning","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2412.00979","title":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance","created":"2024-12-01","cited_by_count":3,"area":"offlinerl"},{"id":"2505.03181","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","created":"2025-05-06","cited_by_count":3,"area":"lr"},{"id":"2505.10760","title":"Counterfactual Behavior Cloning: Offline Imitation Learning from Imperfect Human Demonstrations","created":"2025-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2602.14505","title":"Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC","created":"2026-02-16","cited_by_count":3,"area":"deeprl"},{"id":"2209.06579","title":"C^2:Co-design of Robots via Concurrent Networks Coupling Online and Offline Reinforcement Learning","created":"2022-09-14","cited_by_count":2,"area":"offlinerl"},{"id":"2303.02265","title":"Learning to Influence Human Behavior with Offline Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":"offlinerl"},{"id":"2401.11630","title":"Solving Offline Reinforcement Learning with Decision Tree Regression","created":"2024-01-21","cited_by_count":2,"area":"offlinerl"},{"id":"2405.06063","title":"A Minimalist Prompt for Zero-Shot Policy Learning","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2410.09361","title":"Decision-Point Guided Safe Policy Improvement","created":"2024-10-12","cited_by_count":2,"area":"offlinerl"},{"id":"2410.12172","title":"The State of Robot Motion Generation","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2410.15714","title":"Offline reinforcement learning for job-shop scheduling problems","created":"2024-10-21","cited_by_count":2,"area":"offlinerl"},{"id":"2504.18160","title":"Offline Learning of Controllable Diverse Behaviors","created":"2025-04-25","cited_by_count":2,"area":"offlinerl"},{"id":"2602.06603","title":"The hidden risks of temporal resampling in clinical reinforcement learning","created":"2026-02-06","cited_by_count":2,"area":"offlinerl"},{"id":"2211.01471","title":"Dual Generator Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":1,"area":"offlinerl"},{"id":"2304.09825","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","created":"2023-04-18","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":"2502.06584","title":"Alert: Learning Trigger Functions for Early Classification of Time Series using Deep-RL","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2509.13956","title":"SEG-Parking: Towards Safe, Efficient, and Generalizable Autonomous Parking via End-to-End Offline Reinforcement Learning","created":"2025-09-17","cited_by_count":1,"area":"offlinerl"},{"id":"2510.12638","title":"Expert or not? assessing data quality in offline reinforcement learning","created":"2025-10-14","cited_by_count":1,"area":"offlinerl"},{"id":"2602.02405","title":"Making Expert Reasoning Learnable with Self-Distillation","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2604.07072","title":"Epistemic Robust Offline Reinforcement Learning","created":"2026-04-08","cited_by_count":1,"area":"offlinerl"},{"id":"2301.08794","title":"Robot Skill Learning Via Classical Robotics-Based Generated Datasets: Advantages, Disadvantages, and Future Improvement","created":"2023-01-20","cited_by_count":0,"area":null},{"id":"2406.13376","title":"Efficient Offline Reinforcement Learning: First Imitate, then Improve","created":"2024-06-19","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":"2411.04056","title":"Problem Space Transformations for Out-of-Distribution Generalisation in Behavioural Cloning","created":"2024-11-06","cited_by_count":0,"area":"offlinerl"},{"id":"2505.18083","title":"What Do You Need for Compositional Generalization in Diffusion Planning?","created":"2025-05-23","cited_by_count":0,"area":"offlinerl"},{"id":"2507.19535","title":"Comparing Behavioural Cloning and Reinforcement Learning for Spacecraft Guidance and Control Networks","created":"2025-07-22","cited_by_count":0,"area":"offlinerl"},{"id":"2508.19132","title":"Active Query Selection for Crowd-Based Reinforcement Learning","created":"2025-08-26","cited_by_count":0,"area":"deeprl"},{"id":"2512.17470","title":"Translating the Rashomon Effect to Sequential Decision-Making Tasks","created":"2025-12-19","cited_by_count":0,"area":null},{"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":"2605.13401","title":"Trajectory-Level Data Augmentation for Offline Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2605.24152","title":"Neuro-Inspired Inverse Learning for Planning and Control","created":"2026-05-22","cited_by_count":0,"area":"offlinerl"},{"id":"2606.19481","title":"Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning","created":"2026-06-17","cited_by_count":0,"area":"offlinerl"},{"id":"2606.24160","title":"An Introduction to Causal Reinforcement Learning","created":"2026-06-23","cited_by_count":0,"area":"deeprl"},{"id":"2608.03606","title":"Learning Clinical-Trial Strategy: Offline Policy Training for Decision Agents","created":"2026-08-04","cited_by_count":0,"area":"agents"},{"id":"2609.04066","title":"Subspace Inference Enables Efficient Active Reward Learning from Preferences","created":"2026-09-03","cited_by_count":0,"area":"alignment"},{"id":"2609.30391","title":"From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning","created":"2026-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2609.34426","title":"Q-learning Penalized Transformer for Safe Offline Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"},{"id":"2610.19783","title":"Reinforcement Learning via Advantage Guidance","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}