Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning. This procedure often suffers from exploiting inaccuracies of the learned model. We propose to regularize trajectory optimization by means of a denoising autoencoder that is trained on the same trajectories as the model of the environment. We show that the proposed regularization leads to improved planning with both gradient-based and gradient-free optimizers. We also demonstrate that using regularized trajectory optimization leads to rapid initial learning in a set of popular motor control tasks, which suggests that the proposed approach can be a useful tool for improving sample efficiency.
@article{arxiv.1903.11981,
title = {Regularizing Trajectory Optimization with Denoising Autoencoders},
author = {Rinu Boney and Norman Di Palo and Mathias Berglund and Alexander Ilin and Juho Kannala and Antti Rasmus and Harri Valpola},
journal= {arXiv preprint arXiv:1903.11981},
year = {2019}
}