Detect, understand, act: a neuro-symbolic hierarchical reinforcement learning framework (extended abstract)
File(s)
Accepted version
Supporting information
Author(s)
Mitchener, L
Tuckey, D
Crosby, M
Russo, A
Type
Conference Paper
Abstract
We introduce Detect, Understand, Act (DUA), a neuro-symbolic reinforcement learning framework. The Detect component is composed of a traditional computer vision object detector and tracker. The Act component houses a set of options, high-level actions enacted by pre-trained deep reinforcement learning (DRL) policies. The Understand component provides a novel answer set programming (ASP) paradigm for effectively learning symbolic meta-policies over options using inductive logic programming (ILP). We evaluate our framework on the Animal-AI (AAI) competition testbed, a set of physical cognitive reasoning problems. Given a set of pre-trained DRL policies, DUA requires only a few examples to learn a meta-policy that allows it to improve the state-of-the-art on multiple of the most challenging categories from the testbed. DUA constitutes the first holistic hybrid integration of computer vision, ILP and DRL applied to an AAI-like environment and sets the foundations for further use of ILP in complex DRL challenges.
Date Issued
2022-07-23
Date Acceptance
2022-07-01
Citation
IJCAI International Joint Conference on Artificial Intelligence, 2022, pp.5314-5318
ISBN
9781956792003
ISSN
1045-0823
Publisher
IJCAI
Start Page
5314
End Page
5318
Journal / Book Title
IJCAI International Joint Conference on Artificial Intelligence
Identifier
https://www.ijcai.org/proceedings/2022/742
Source
THE 31ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE
Publication Status
Published
Start Date
2022-07-23
Finish Date
2022-07-29
Coverage Spatial
Vienna, Austria
Date Publish Online
2022-07-23