@InCollection{Supelec726,
author = {Edouard Klein and Matthieu Geist and Olivier Pietquin},
title = {Batch, Off-policy and Model-free Apprenticeship Learning},
year = {2011},
booktitle = {Proceedings of the European Workshop on Reinforcement Learning (EWRL 2011)},
publisher = {Springer Verlag - Heidelberg Berlin},
pages = {12 pages},
month = {september},
series = {Lecture Notes in Computer Science (LNCS)},
address = {Athens (Greece)},
url = {http://www.metz.supelec.fr//metz/personnel/geist_mat/pdfs/supelec726.pdf},
abstract = {This paper addresses the problem of apprenticeship learning, that is learning control policies from demonstration by an expert. An efficient framework for it is inverse reinforcement learning (IRL). Based on the assumption that the expert maximizes a utility function, IRL aims at learning the underlying reward from example trajectories. Many IRL algorithms assume that the reward function is linearly parameterized and rely on the computation of some associated feature expectations, which is done through Monte Carlo simulation. However, this assumes to have full trajectories for the expert policy as well as at least a generative model for intermediate policies. In this paper, we introduce a temporal difference method, namely LSTD-mu, to compute these feature expectations. This allows extending apprenticeship learning to a batch and off-policy setting.}
}