English

Regularizing Trajectory Optimization with Denoising Autoencoders

Machine Learning 2019-12-30 v3 Robotics Machine Learning

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.

Keywords

Cite

@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}
}

Comments

NeurIPS 2019

R2 v1 2026-06-23T08:22:07.938Z