UAI 2020poster1 citations

Provably Efficient Third-Person Imitation from Offline Observation

Aaron Zweig, Joan Bruna

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 the online setting.

BibTeX
@InProceedings{pmlr-v124-zweig20a,
  title = 	 {Provably Efficient Third-Person Imitation from Offline Observation},
  author =       {Zweig, Aaron and Bruna, Joan},
  booktitle = 	 {Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)},
  pages = 	 {1228--1237},
  year = 	 {2020},
  editor = 	 {Peters, Jonas and Sontag, David},
  volume = 	 {124},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {03--06 Aug},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v124/zweig20a/zweig20a.pdf},
  url = 	 {https://proceedings.mlr.press/v124/zweig20a.html},
  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 the online setting.}
}
Provably Efficient Third-Person Imitation from Offline Observation · UAI 2020