# Improving Model-Based Control and Active Exploration with Reconstruction Uncertainty Optimization

arXiv: https://arxiv.org/abs/1812.03955 · HTML: https://mlsanity.com/paper/1812.03955/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2018.

## Built on by (most cited first, 1 of 1)

- [SAFARI: Safe and Active Robot Imitation Learning with Imagination](https://mlsanity.com/paper/2011.09586/) (2020)

## Abstract (arXiv)

Model based predictions of future trajectories of a dynamical system often suffer from inaccuracies, forcing model based control algorithms to re-plan often, thus being computationally expensive, suboptimal and not reliable. In this work, we propose a model agnostic method for estimating the uncertainty of a model?s predictions based on reconstruction error, using it in control and exploration. As our experiments show, this uncertainty estimation can be used to improve control performance on a wide variety of environments by choosing predictions of which the model is confident. It can also be used for active learning to explore more efficiently the environment by planning for trajectories with high uncertainty, allowing faster model learning.