# Regularizing Trajectory Optimization with Denoising Autoencoders

arXiv: https://arxiv.org/abs/1903.11981 · HTML: https://mlsanity.com/paper/1903.11981/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2019.

## Built on by (most cited first, 2 of 2)

- [Gradient-Based Trajectory Optimization With Learned Dynamics](https://mlsanity.com/paper/2204.04558/) (2022)
- [SAFARI: Safe and Active Robot Imitation Learning with Imagination](https://mlsanity.com/paper/2011.09586/) (2020)

## Abstract (arXiv)

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.