Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality. (arXiv:2110.14754v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2110.14754

Most existing imitation learning approaches assume the demonstrations are
drawn from experts who are optimal, but relaxing this assumption enables us to
use a wider range of data. Standard imitation learning may learn a suboptimal
policy from demonstrations with varying optimality. Prior works use confidence
scores or rankings to capture beneficial information from demonstrations with
varying optimality, but they suffer from many limitations, e.g., manually
annotated confidence scores or high average optimality of demonstrations. In
this paper, we propose a …

arxiv confidence learning