Recent work by Jarrett et al. attempts to frame the problem of offline imitation learning (IL) as one of learning a joint energy-based model, with the hope of out-performing standard behavioral cloning. We suggest that notational issues obscure how the psuedo-state visitation distribution the authors propose to optimize might be disconnected from the policy's true state visitation distribution. We further construct natural examples where the parameter coupling advocated by Jarrett et al. leads to inconsistent estimates of the expert's policy, unlike behavioral cloning.
Cite
@article{arxiv.2110.02063,
title = {A Critique of Strictly Batch Imitation Learning},
author = {Gokul Swamy and Sanjiban Choudhury and J. Andrew Bagnell and Zhiwei Steven Wu},
journal= {arXiv preprint arXiv:2110.02063},
year = {2021}
}