Direct Policy Iteration with Demonstrations
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Special Track on Machine Learning. Pages 3380-3385.
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.
@inproceedings{ijcai2015p476,
title = {Direct Policy Iteration with Demonstrations},
author = {Chemali, Jessica and Lazaric, Alessandro},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {3380--3385},
year = {2015},
month = {7},
note = {Special Track on Machine Learning},
url = {https://ijcai.org/proceedings/2015/476},
}
TY - CPAPER TI - Direct Policy Iteration with Demonstrations AU - Chemali, Jessica AU - Lazaric, Alessandro T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 3380 EP - 3385 UR - https://ijcai.org/proceedings/2015/476 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
