| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Direct Policy Iteration with Demonstrations
Abstract : We consider the problem of learning the optimal policy of an unknown Markov decision process (MDP) when expert demonstrations are available along with interaction samples. We build on classification-based policy iteration to perform a seamless integration of interaction and expert data, thus obtaining an algorithm which can benefit from both sources of information at the same time. Furthermore , we provide a full theoretical analysis of the performance across iterations providing insights on how the algorithm works. Finally, we report an empirical evaluation of the algorithm and a comparison with the state-of-the-art algorithms.
Cited literature [13 references]
https://hal.inria.fr/hal-01237659
Contributor : Alessandro Lazaric Connect in order to contact the contributor
Submitted on : Thursday, December 3, 2015 - 3:46:20 PM
Last modification on : Thursday, January 20, 2022 - 4:12:31 PM
Long-term archiving on: : Saturday, April 29, 2017 - 7:49:10 AM
Contributor : Alessandro Lazaric Connect in order to contact the contributor
Submitted on : Thursday, December 3, 2015 - 3:46:20 PM
Last modification on : Thursday, January 20, 2022 - 4:12:31 PM
Long-term archiving on: : Saturday, April 29, 2017 - 7:49:10 AM
File
DPID_CameraReady.pdf
Files produced by the author(s)