{"total":19,"rows":[{"id":"2405.18080","title":"HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","created":"2024-05-28","cited_by_count":14,"area":"offlinerl"},{"id":"2410.23450","title":"Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning","created":"2024-10-30","cited_by_count":13,"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":"2407.04285","title":"Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling","created":"2024-07-05","cited_by_count":7,"area":"offlinerl"},{"id":"2411.01168","title":"Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization","created":"2024-11-02","cited_by_count":6,"area":"offlinerl"},{"id":"2409.08062","title":"Q-value Regularized Decision ConvFormer for Offline Reinforcement Learning","created":"2024-09-12","cited_by_count":4,"area":"offlinerl"},{"id":"2507.10174","title":"Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?","created":"2025-07-14","cited_by_count":2,"area":"offlinerl"},{"id":"2511.02567","title":"Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning","created":"2025-11-04","cited_by_count":2,"area":"offlinerl"},{"id":"2411.01146","title":"Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","created":"2024-11-02","cited_by_count":1,"area":"offlinerl"},{"id":"2411.11364","title":"Continual Task Learning through Adaptive Policy Self-Composition","created":"2024-11-18","cited_by_count":1,"area":"offlinerl"},{"id":"2504.03800","title":"Decision SpikeFormer: Spike-Driven Transformer for Decision Making","created":"2025-04-04","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":"2602.07441","title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","created":"2026-02-07","cited_by_count":1,"area":"offlinerl"},{"id":"2502.01778","title":"GNN-DT: Graph Neural Network Enhanced Decision Transformer for Efficient Optimization in Dynamic Environments","created":"2025-02-03","cited_by_count":0,"area":"offlinerl"},{"id":"2509.15498","title":"Mental Accounts for Actions: EWA-Inspired Attention in Decision Transformers","created":"2025-09-19","cited_by_count":0,"area":"offlinerl"},{"id":"2510.05285","title":"Adjusting the Output of Decision Transformer with Action Gradient","created":"2025-10-06","cited_by_count":0,"area":"offlinerl"},{"id":"2511.09173","title":"Target-Aligned Fusion for Decision-Sequence Learning under Dynamics Shift","created":"2025-11-12","cited_by_count":0,"area":"offlinerl"},{"id":"2608.28878","title":"Hybrid Offline-Online Multi-Agent Decision Transformers for Wireless Resource Management","created":"2026-08-28","cited_by_count":0,"area":"offlinerl"},{"id":"2609.34426","title":"Q-learning Penalized Transformer for Safe Offline Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}