离线发现多任务轨迹中的可解释技能
Offline Discovery of Interpretable Skills from Multi-Task Trajectories
AI总结：
LOKI通过三阶段端到端学习框架，从多任务离线数据中发现可解释的技能，实现高成功率和语义有意义的技能组合。
摘要：
分层模仿学习是一种从演示中获取复杂机器人行为的强大范式。然而，一个核心挑战在于从长时间跨度的多任务离线数据中发现可重用的技能，尤其是在数据缺乏显式奖励或子任务注释的情况下。在本工作中，我们引入了LOKI，一种三阶段端到端学习框架，用于离线技能发现和分层模仿。该框架首先进行一个两阶段的弱监督技能发现过程：第一阶段通过一种受对齐约束的向量量化变分自编码器进行粗略的、任务感知的宏分段，该变分自编码器由弱任务标签引导。第二阶段则通过自监督序列模型在微观层面细化这些段落，并通过迭代聚类过程来巩固技能边界。第三阶段则利用这些精确的边界来构建一个基于选项的分层策略——包含一个学习得到的终止条件beta，用于显式地切换技能。LOKI在具有挑战性的D4RL厨房基准测试中实现了高成功率，并优于标准HIL基线。此外，我们证明所发现的技能在语义上是有意义的，符合人类直觉，并且具有组合性，通过成功地将它们按顺序排列来解决一个新出现的未见过的任务。
英文摘要：
Hierarchical Imitation Learning is a powerful paradigm for acquiring complex robot behaviors from demonstrations. A central challenge, however, lies in discovering reusable skills from long-horizon, multi-task offline data, especially when the data lacks explicit rewards or subtask annotations. In this work, we introduce LOKI, a three-stage end-to-end learning framework designed for offline skill discovery and hierarchical imitation. The framework commences with a two-stage, weakly supervised skill discovery process: Stage one performs coarse, task-aware macro-segmentation by employing an alignment-enforced Vector Quantized VAE guided by weak task labels. Stage two then refines these segments at a micro-level using a self-supervised sequential model, followed by an iterative clustering process to consolidate skill boundaries. The third stage then leverages these precise boundaries to construct a hierarchical policy within an option-based framework-complete with a learned termination condition beta for explicit skill switching. LOKI achieves high success rates on the challenging D4RL Kitchen benchmark and outperforms standard HIL baselines. Furthermore, we demonstrate that the discovered skills are semantically meaningful, aligning with human intuition, and exhibit compositionality by successfully sequencing them to solve a novel, unseen task.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
