解决模仿学习在分布偏移下的安全问题，提升复杂环境中的鲁棒性。
Distributionally Robust and Safe Imitation Learning
- 用泰勒展开模仿学习缓解策略导致的分布偏移
- 结合鲁棒自适应控制应对不确定性带来的偏移
- 适合高安全性要求的无人机等自主系统
模仿学习（IL）在复杂决策任务中取得显著进展，但其性能对分布偏移高度敏感，可能引发重大安全风险。本文提出一种分布鲁棒且安全的模仿学习框架，显式处理策略诱导和不确定性诱导的分布偏移。方法融合泰勒展开模仿学习（TaSIL）以缓解策略相关偏移，并采用分布鲁棒自适应控制应对不确定性偏移。该架构将模仿学习问题建模为在分布不确定性下优化性能的同时系统性满足安全约束。在无人飞行器（UAV）案例研究中验证了有效性：无人机在不确定环境中执行任务并避开危险区域。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。