MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts
arxiv(2023)
摘要
Imitation learning has been widely applied to various autonomous systems
thanks to recent development in interactive algorithms that address covariate
shift and compounding errors induced by traditional approaches like behavior
cloning. However, existing interactive imitation learning methods assume access
to one perfect expert. Whereas in reality, it is more likely to have multiple
imperfect experts instead. In this paper, we propose MEGA-DAgger, a new DAgger
variant that is suitable for interactive learning with multiple imperfect
experts. First, unsafe demonstrations are filtered while aggregating the
training data, so the imperfect demonstrations have little influence when
training the novice policy. Next, experts are evaluated and compared on
scenarios-specific metrics to resolve the conflicted labels among experts.
Through experiments in autonomous racing scenarios, we demonstrate that policy
learned using MEGA-DAgger can outperform both experts and policies learned
using the state-of-the-art interactive imitation learning algorithms such as
Human-Gated DAgger. The supplementary video can be found at
.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要