author = {Bilal PIOT and Matthieu Geist and Olivier Pietquin},
title = {{Difference of Convex Functions Programming Applied to Control with Expert Data}},
year = {2016},
howpublished = {arxiv},
url = {http://arxiv.org/abs/1606.01128},
abstract = {This paper shows how Difference of Convex functions (DC) programming can improve the performance of some Reinforcement Learning (RL) algorithms using expert data and Learning from Demonstrations (LfD) algorithms. This is principally due to the fact that the norm of the Optimal Bellman Residual (OBR), which is one of the main component of the algorithms considered, is DC. The slight performance improvement is shown on two algorithms, namely Reward-regularized Classification for Apprenticeship Learning (RCAL) and Reinforcement Learning with Expert Demonstrations (RLED), through experiments on generic Markov Decision Processes (MDP) called Garnets. }