Predictive Control Using Learned State Space Models via Rolling Horizon Evolution
Machine Learning
2021-06-29 v1 Artificial Intelligence
Abstract
A large part of the interest in model-based reinforcement learning derives from the potential utility to acquire a forward model capable of strategic long term decision making. Assuming that an agent succeeds in learning a useful predictive model, it still requires a mechanism to harness it to generate and select among competing simulated plans. In this paper, we explore this theme combining evolutionary algorithmic planning techniques with models learned via deep learning and variational inference. We demonstrate the approach with an agent that reliably performs online planning in a set of visual navigation tasks.
Cite
@article{arxiv.2106.13911,
title = {Predictive Control Using Learned State Space Models via Rolling Horizon Evolution},
author = {Alvaro Ovalle and Simon M. Lucas},
journal= {arXiv preprint arXiv:2106.13911},
year = {2021}
}
Comments
Accepted at the Bridging the Gap Between AI Planning and Reinforcement Learning (PRL) Workshop at ICAPS 2021