English

Imitation Learning via Off-Policy Distribution Matching

Machine Learning 2019-12-12 v1 Machine Learning

Abstract

When performing imitation learning from expert demonstrations, distribution matching is a popular approach, in which one alternates between estimating distribution ratios and then using these ratios as rewards in a standard reinforcement learning (RL) algorithm. Traditionally, estimation of the distribution ratio requires on-policy data, which has caused previous work to either be exorbitantly data-inefficient or alter the original objective in a manner that can drastically change its optimum. In this work, we show how the original distribution ratio estimation objective may be transformed in a principled manner to yield a completely off-policy objective. In addition to the data-efficiency that this provides, we are able to show that this objective also renders the use of a separate RL optimization unnecessary.Rather, an imitation policy may be learned directly from this objective without the use of explicit rewards. We call the resulting algorithm ValueDICE and evaluate it on a suite of popular imitation learning benchmarks, finding that it can achieve state-of-the-art sample efficiency and performance.

Keywords

Cite

@article{arxiv.1912.05032,
  title  = {Imitation Learning via Off-Policy Distribution Matching},
  author = {Ilya Kostrikov and Ofir Nachum and Jonathan Tompson},
  journal= {arXiv preprint arXiv:1912.05032},
  year   = {2019}
}
R2 v1 2026-06-23T12:42:08.911Z