DIGIC: Domain Generalizable Imitation Learning by Causal Discovery

arXiv:2402.18910v1 Announce Type: new
Abstract: Causality has been combined with machine learning to produce robust representations for domain generalization. Most existing methods of this type require massive data from multiple domains to identify causal features by cross-domain variations, which can be expensive or even infeasible and may lead to misidentification in some cases. In this work, we make a different attempt by leveraging the demonstration data distribution to discover the causal features for a domain generalizable policy. We design a …

abstract arxiv causality cs.ai cs.lg data discovery domain domains features identify imitation learning machine machine learning massive multiple robust stat.me type