分布鲁棒且安全的模仿学习
Distributionally Robust and Safe Imitation Learning
浏览论文内容
中文总结 AI 辅助
研究针对模仿学习对分布变化敏感及安全风险问题，提出分布鲁棒且安全的模仿学习框架，利用泰勒级数模仿学习和分布鲁棒自适应控制应对不同诱导变化，在无人机案例中验证了方法有效性。
中文摘要 AI 辅助
模仿学习在复杂决策任务中取得显著成功，但其性能对分布变化敏感，存在安全风险。我们提出一个分布鲁棒且安全的模仿学习框架，明确应对策略诱导和不确定性诱导的分布变化。该方法利用泰勒级数模仿学习减轻策略诱导变化，用分布鲁棒自适应控制处理不确定性诱导变化，在无人机案例中验证了其有效性。
英文摘要
Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally robust and safe IL framework that explicitly addresses both policy-induced and uncertainty-induced distribution shifts. Our approach develops a unified framework leveraging Taylor Series Imitation Learning (TaSIL) to mitigate policy-induced shifts and distributionally robust adaptive control to handle uncertainty-induced shifts. This architecture enables the formulation of an IL problem that optimizes performance under distributional uncertainty while systematically accounting for safety constraints. We demonstrate the effectiveness of the proposed approach on an unmanned aerial vehicle (UAV) case study where the UAV performs a task in an uncertain environment while avoiding unsafe regions.
发表机构
- University of California Berkeley（加利福尼亚大学伯克利分校）
- University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。
