RLAR: A Reinforcement Learning Abductive Reasoner

Mostafa ElHayani

2024

Abstract

Machine learning (ML) algorithms are the foundation of the modern AI environment. They are renowned for their capacity to solve complicated problems and generalize across a wide range of datasets. Nevertheless, a noteworthy disadvantage manifests itself as a lack of explainability. Symbolic AI is at the other extreme of the spectrum; in this case, every inference is a proof, allowing for transparency and traceability throughout the decision-making process. This paper proposes the Reinforcement Learning Abductive Reasoner (RLAR). A combination of modern and symbolic AI algorithms aimed to bridge the gap and utilize the best features of both methods. A case study has been chosen to test the implementation of the proposed reasoner. A knowledge-base (KB) vectorization step is implemented, and a Machine Learning model architecture is built to learn explanation inference. Furthermore, a simple abductive reasoner is also implemented to compare both approaches.

Paper Citation

in Harvard Style

ElHayani M. (2024). RLAR: A Reinforcement Learning Abductive Reasoner. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 972-979. DOI: 10.5220/0012425000003636

in Bibtex Style

@conference{icaart24,
author={Mostafa ElHayani},
title={RLAR: A Reinforcement Learning Abductive Reasoner},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={972-979},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012425000003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - RLAR: A Reinforcement Learning Abductive Reasoner
SN - 978-989-758-680-4
AU - ElHayani M.
PY - 2024
SP - 972
EP - 979
DO - 10.5220/0012425000003636
PB - SciTePress