@inproceedings{audiffren2014messi,
abstract = {A popular approach to apprenticeship learning (AL) is to formulate it as an inverse reinforcement learning (IRL) problem. The MaxEnt-IRL algorithm successfully integrates the maximum entropy principle into IRL and unlike its predecessors, it resolves the ambiguity arising from the fact that a possibly large number of policies could match the expert's behavior. In this paper, we study an AL setting in which in addition to the expert's trajectories, a number of unsupervised trajectories is available. We introduce MESSI, a novel algorithm that combines MaxEnt-IRL with principles coming from semi-supervised learning. In particular, MESSI integrates the unsupervised data into the MaxEnt-IRL framework using a pairwise penalty on trajectories. Empirical results in a highway driving and grid-world problems indicate that MESSI is able to take advantage of the unsupervised trajectories and improve the performance of MaxEnt-IRL.},
author = {Audiffren, Julien and Valko, Michal and Lazaric, Alessandro and Ghavamzadeh, Mohammad},
booktitle = {NIPS Workshop on Novel Trends and Applications in Reinforcement Learning},
title = {{MESSI: Maximum Entropy Semi-Supervised Inverse Reinforcement Learning}},
year = {2014}
}