Provably Efficient Third-Person Imitation from Offline Observation

02/27/2020
by   Aaron Zweig, et al.
4

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset