发表机构
Hanyang University（汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PathBridger是一种分层离线目标条件强化学习方法，通过构建状态空间桥并结合逆动力学模型解码为动作块，在OGBench任务尤其是多目标Cube操作任务上性能显著提升。
AI 中文摘要
离线目标条件强化学习（GCRL）旨在完全从固定轨迹数据中学习实现不同目标的策略。长时序离线GCRL仍具挑战性，因为稀疏的目标达成信号需在多步间传播，且执行错误无法通过额外环境交互修正。现有方法通过改进长程价值估计或利用子目标、选项、动作块缩短有效决策时域来应对这些挑战。然而，在若干分层方法中，所选子目标仅指定去向，中间状态空间路径仍隐含在端点条件的低层策略中。为解决这一接口问题，我们提出PathBridger，一种分层离线GCRL方法，其明确将子目标选择与短时序执行关联。PathBridger构建指向所选中间端点的状态空间桥，并通过逆动力学模型将其解码为可执行的短动作块。在评估的OGBench任务上的实验显示出强劲的整体性能，尤其在多目标Cube操作任务上取得了显著提升。代码：this https URL
英文摘要
Offline goal-conditioned reinforcement learning (GCRL) aims to learn policies for reaching diverse goals entirely from fixed trajectory data. Long-horizon offline GCRL remains challenging because sparse goal-reaching signals must be propagated over many steps, while execution errors cannot be corrected through additional environment interaction. Existing methods address these challenges by improving long-range value estimation or reducing the effective decision horizon through subgoals, options, and action chunks. In several hierarchical methods, however, a selected subgoal specifies where to go, while the intervening state-space path remains implicit in an endpoint-conditioned low-level policy. To address this interface, we propose PathBridger, a hierarchical offline GCRL method that explicitly connects subgoal selection to short-horizon execution. PathBridger constructs a state-space bridge toward the selected intermediate endpoint and decodes it into a short executable action chunk using an inverse dynamics model. Experiments across the evaluated OGBench tasks demonstrate strong aggregate performance, with particularly large gains on the multi-object Cube manipulation tasks. Code: https://github.com/SChoish/PathBridger
Comments14 pages, 2 figures. Code: https://github.com/SChoish/PathBridger
