The Logical Options Framework
Artificial Intelligence
2021-02-26 v1 Machine Learning
Robotics
Abstract
Learning composable policies for environments with complex rules and tasks is a challenging problem. We introduce a hierarchical reinforcement learning framework called the Logical Options Framework (LOF) that learns policies that are satisfying, optimal, and composable. LOF efficiently learns policies that satisfy tasks by representing the task as an automaton and integrating it into learning and planning. We provide and prove conditions under which LOF will learn satisfying, optimal policies. And lastly, we show how LOF's learned policies can be composed to satisfy unseen tasks with only 10-50 retraining steps. We evaluate LOF on four tasks in discrete and continuous domains, including a 3D pick-and-place environment.
Cite
@article{arxiv.2102.12571,
title = {The Logical Options Framework},
author = {Brandon Araki and Xiao Li and Kiran Vodrahalli and Jonathan DeCastro and Micah J. Fry and Daniela Rus},
journal= {arXiv preprint arXiv:2102.12571},
year = {2021}
}
Comments
23 pages, 19 figures