高效在线策略适应的超级决策 Transformer（英文版）

英文标题：Hyper-Decision Transformer for Efficient Online Policy Adaptation中文摘要：Hyper-Decision Transformer (HDT) framework proposes an adaptation module initialized by a hyper-network to enable efficient adaptation to novel tasks for offline reinforcement learning, demonstrating better performance than state-of-the-art baselines in terms of task success rates.英文摘要：Decision Transformers (DT) have demonstrated strong performances in offlinereinforcement learning settings, but quickly adapting to unseen