TY - CONF
T1 - Provably efficient third-person imitation from offline observation
AU - Zweig, Aaron
AU - Bruna, Joan
N1 - Funding Information:
This work partially supported by the Alfred P. Sloan Foundation, NSF RI-1816753, NSF CAREER CIF 1845360, NSF CHS-1901091, Samsung Electronics, and the Institute for Advanced Study.
Funding Information:
This work partially supported by the Alfred P. Sloan Foundation, NSF RI-1816753, NSF CAREER CIF 1845360, NSF CHS-1901091, Samsung Electronics, and
Publisher Copyright:
© Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence, UAI 2020. All rights reserved.
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85101601498&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101601498&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85101601498
SP - 1228
EP - 1237
T2 - 36th Conference on Uncertainty in Artificial Intelligence, UAI 2020
Y2 - 3 August 2020 through 6 August 2020
ER -