English

A Critique of Strictly Batch Imitation Learning

Machine Learning 2021-10-06 v1

Abstract

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\textit{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}
}
R2 v1 2026-06-24T06:38:12.582Z