Neuro-Symbolic Reinforcement Learning with First-Order Logic
Daiki Kimura, Masaki Ono, Subhajit Chaudhury, Ryosuke Kohita, Akifumi Wachi, Don Joven Agravante, Michiaki Tatsubori, Asim Munawar
Abstract
Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules in their differentiable network. The method is first to extract first-order logical facts from text observation and external word meaning network (ConceptNet), then train a policy in the network with directly interpretable logical operators. Our experimental results show RL training with the proposed method converges significantly faster than other state-of-the-art neuro-symbolic methods in a TextWorld benchmark.
BibTeX
@inproceedings{kimura-etal-2021-neuro,
title = "Neuro-Symbolic Reinforcement Learning with First-Order Logic",
author = "Kimura, Daiki and
Ono, Masaki and
Chaudhury, Subhajit and
Kohita, Ryosuke and
Wachi, Akifumi and
Agravante, Don Joven and
Tatsubori, Michiaki and
Munawar, Asim and
Gray, Alexander",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.283/",
doi = "10.18653/v1/2021.emnlp-main.283",
pages = "3505--3511"
}