Regularizing Trajectory Optimization with Denoising Autoencoders
Abstract
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.
Cite
Text
Boney et al. "Regularizing Trajectory Optimization with Denoising Autoencoders." Neural Information Processing Systems, 2019.Markdown
[Boney et al. "Regularizing Trajectory Optimization with Denoising Autoencoders." Neural Information Processing Systems, 2019.](https://mlanthology.org/neurips/2019/boney2019neurips-regularizing/)BibTeX
@inproceedings{boney2019neurips-regularizing,
title = {{Regularizing Trajectory Optimization with Denoising Autoencoders}},
author = {Boney, Rinu and Di Palo, Norman and Berglund, Mathias and Ilin, Alexander and Kannala, Juho and Rasmus, Antti and Valpola, Harri},
booktitle = {Neural Information Processing Systems},
year = {2019},
pages = {2859-2869},
url = {https://mlanthology.org/neurips/2019/boney2019neurips-regularizing/}
}