{"total":59,"rows":[{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"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":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"area":"offlinerl"},{"id":"2404.19264","title":"DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets","created":"2024-04-30","cited_by_count":49,"area":null},{"id":"2307.11620","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","created":"2023-07-21","cited_by_count":43,"area":"offlinerl"},{"id":"2407.20109","title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":42,"area":"diffusion"},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2601.00844","title":"Value-guided action planning with JEPA world models","created":"2025-12-28","cited_by_count":21,"area":"wm"},{"id":"2306.04220","title":"Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL","created":"2023-06-07","cited_by_count":18,"area":"offlinerl"},{"id":"2309.12716","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","created":"2023-09-22","cited_by_count":17,"area":"offlinerl"},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"id":"2509.06782","title":"Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning","created":"2025-09-08","cited_by_count":15,"area":"offlinerl"},{"id":"2306.00867","title":"IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control","created":"2023-06-01","cited_by_count":14,"area":"offlinerl"},{"id":"2505.06861","title":"Efficient Robotic Policy Learning via Latent Space Backward Planning","created":"2025-05-11","cited_by_count":14,"area":null},{"id":"2506.21427","title":"Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning","created":"2025-06-26","cited_by_count":14,"area":"diffusion"},{"id":"2306.05726","title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning","created":"2023-06-09","cited_by_count":10,"area":"offlinerl"},{"id":"2405.11647","title":"Hummer: Towards Limited Competitive Preference Dataset","created":"2024-05-19","cited_by_count":10,"area":"alignment"},{"id":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","cited_by_count":10,"area":"deeprl"},{"id":"2303.08789","title":"PLEX: Making the Most of the Available Data for Robotic Manipulation Pretraining","created":"2023-03-15","cited_by_count":9,"area":null},{"id":"2412.18855","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","created":"2024-12-25","cited_by_count":9,"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":"2410.01954","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","created":"2024-10-02","cited_by_count":8,"area":"offlinerl"},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2306.08900","title":"Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization","created":"2023-06-15","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":"2510.15382","title":"Towards Robust Zero-Shot Reinforcement Learning","created":"2025-10-17","cited_by_count":7,"area":"deeprl"},{"id":"2307.02752","title":"Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-07-06","cited_by_count":6,"area":"offlinerl"},{"id":"2407.05424","title":"BiRoDiff: Diffusion policies for bipedal robot locomotion on unseen terrains","created":"2024-07-07","cited_by_count":6,"area":"diffusion"},{"id":"2410.03408","title":"Predictive Coding for Decision Transformer","created":"2024-10-04","cited_by_count":6,"area":"offlinerl"},{"id":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"id":"2507.14497","title":"Efficient Whole Slide Pathology VQA via Token Compression","created":"2025-07-19","cited_by_count":6,"area":"mllm"},{"id":"2506.18847","title":"Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planning","created":"2025-06-23","cited_by_count":5,"area":"offlinerl"},{"id":"2405.04307","title":"Improving Offline Reinforcement Learning with Inaccurate Simulators","created":"2024-05-07","cited_by_count":4,"area":"offlinerl"},{"id":"2412.20519","title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning","created":"2024-12-29","cited_by_count":4,"area":"offlinerl"},{"id":"2501.15085","title":"Data Center Cooling System Optimization Using Offline Reinforcement Learning","created":"2025-01-25","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":"2508.21104","title":"PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning","created":"2025-08-28","cited_by_count":4,"area":"agents"},{"id":"2402.03923","title":"Return-Aligned Decision Transformer","created":"2024-02-06","cited_by_count":3,"area":"offlinerl"},{"id":"2408.07245","title":"q-exponential family for policy optimization","created":"2024-08-14","cited_by_count":2,"area":"deeprl"},{"id":"2409.03996","title":"Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2410.16517","title":"RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space","created":"2024-10-21","cited_by_count":2,"area":"deeprl"},{"id":"2410.19982","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","created":"2024-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2503.21018","title":"Offline Action-Free Learning of Ex-BMDPs by Comparing Diverse Datasets","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2605.22711","title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-21","cited_by_count":2,"area":"offlinerl"},{"id":"2607.07855","title":"NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2405.14374","title":"State-Constrained Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":1,"area":"offlinerl"},{"id":"2406.04534","title":"Strategically Conservative Q-Learning","created":"2024-06-06","cited_by_count":1,"area":"offlinerl"},{"id":"2506.08463","title":"How to Provably Improve Return Conditioned Supervised Learning?","created":"2025-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2510.22027","title":"Online Optimization for Offline Safe Reinforcement Learning","created":"2025-10-24","cited_by_count":1,"area":"offlinerl"},{"id":"2609.02237","title":"Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL","created":"2026-09-02","cited_by_count":1,"area":"offlinerl"},{"id":"2404.06188","title":"Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning","created":"2024-04-09","cited_by_count":0,"area":"offlinerl"},{"id":"2406.03324","title":"UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning","created":"2024-06-05","cited_by_count":0,"area":"offlinerl"},{"id":"2406.07541","title":"CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning","created":"2024-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2502.00850","title":"Dual Alignment Maximin Optimization for Offline Model-based RL","created":"2025-02-02","cited_by_count":0,"area":"offlinerl"},{"id":"2606.17011","title":"ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"vla"},{"id":"2606.21136","title":"Horizon Adaptive Offline Policy Learning via Value Stitching","created":"2026-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2609.19414","title":"Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation","created":"2026-09-16","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}