Loading [MathJax]/extensions/MathMenu.js
Towards Neural-Symbolic Learning to support Human-Agent Operations | IEEE Conference Publication | IEEE Xplore

Towards Neural-Symbolic Learning to support Human-Agent Operations


Abstract:

This paper investigates neural-symbolic policy learning for information fusion in distributed human-agent operations. The architecture integrates a pre-trained neural net...Show More

Abstract:

This paper investigates neural-symbolic policy learning for information fusion in distributed human-agent operations. The architecture integrates a pre-trained neural network for feature extraction, with a state-of-the-art symbolic Inductive Logic Programming (ILP) system to learn policies, expressed as a set of logical rules. We firstly outline the challenge of policy learning within a military environment, by investigating the accuracy and confidence of neural network predictions given data outside the training distribution. Secondly, we introduce a neural-symbolic integration for policy learning and demonstrate that the symbolic ILP component, when considering the length of the learned policy rules, can generalise and learn a robust policy despite unstructured data observed at policy learning time originating from a different distribution than observed during training.
Date of Conference: 01-04 November 2021
Date Added to IEEE Xplore: 02 December 2021
ISBN Information:
Conference Location: Sun City, South Africa

Funding Agency:

IBM Research Europe, Hursley, UK
Imperial College London, London, UK
Imperial College London, London, UK
Imperial College London, London, UK
Imperial College London, London, UK
Army Research Laboratory, Adelphi, MD, USA

IBM Research Europe, Hursley, UK
Imperial College London, London, UK
Imperial College London, London, UK
Imperial College London, London, UK
Imperial College London, London, UK
Army Research Laboratory, Adelphi, MD, USA

Contact IEEE to Subscribe

References

References is not available for this document.