Provably efficient third-person imitation from offline observation

Aaron Zweig, Joan Bruna

Research output: Contribution to conferencePaperpeer-review

Abstract

Domain adaptation in imitation learning represents an essential step towards improving generalizability. However, even in the restricted setting of third-person imitation where transfer is between isomorphic Markov Decision Processes, there are no strong guarantees on the performance of transferred policies. We present problem-dependent, statistical learning guarantees for third-person imitation from observation in an offline setting, and a lower bound on performance in an online setting.

Original languageEnglish (US)
Pages1228-1237
Number of pages10
StatePublished - 2020
Event36th Conference on Uncertainty in Artificial Intelligence, UAI 2020 - Virtual, Online
Duration: Aug 3 2020Aug 6 2020

Conference

Conference36th Conference on Uncertainty in Artificial Intelligence, UAI 2020
CityVirtual, Online
Period8/3/208/6/20

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this