Towards an Interpretable Hierarchical Agent Framework using Semantic Goals
Loading...
Links to Files
Author/Creator
Author/Creator ORCID
Date
2022-10-16
Type of Work
Department
Program
Citation of Original Publication
Rights
This work was written as part of one of the author's official duties as an Employee of the United States Government and is therefore a work of the United States Government. In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. Law.
Public Domain Mark 1.0
Public Domain Mark 1.0
Subjects
Abstract
Learning to solve long horizon temporally extended tasks
with reinforcement learning has been a challenge for several
years now. We believe that it is important to leverage both the
hierarchical structure of complex tasks and to use expert supervision whenever possible to solve such tasks. This work
introduces an interpretable hierarchical agent framework by
combining planning and semantic goal directed reinforcement learning. We assume access to certain spatial and haptic predicates and construct a simple and powerful semantic
goal space. These semantic goal representations are more interpretable, making expert supervision and intervention easier. They also eliminate the need to write complex, dense reward functions thereby reducing human engineering effort.
We evaluate our framework on a robotic block manipulation
task and show that it performs better than other methods, including both sparse and dense reward functions. We also suggest some next steps and discuss how this framework makes
interaction and collaboration with humans easier.