The Logical Options Framework

Brandon Araki, Xiao Li, Kiran Vodrahalli, Jonathan DeCastro, J Micah Fry, Daniela Rus

Keywords: reinforcement learning, hierarchical methods, formal methods, formal logic

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.

One-sentence Summary: We introduce a composable hierarchical method for learning tasks specified by formal logic, as well as proofs and conditions for satisfaction and optimality.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=RBNIrPmvio