We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games. The demonstration for LOA experiments consists of a web-based interactive platform for text-based games and visualization for acquired knowledge for improving interpretability for trained rules. This demonstration also provides a comparison module with other neuro-symbolic approaches as well as non-symbolic state-of-the-art agent models on the same text-based games. Our LOA also provides open-sourced implementation in Python for the reinforcement learning environment to facilitate an experiment for studying neuro-symbolic agents. Code: https://github.com/ibm/loa
@article{arxiv.2110.10973,
title = {LOA: Logical Optimal Actions for Text-based Interaction Games},
author = {Daiki Kimura and Subhajit Chaudhury and Masaki Ono and Michiaki Tatsubori and Don Joven Agravante and Asim Munawar and Akifumi Wachi and Ryosuke Kohita and Alexander Gray},
journal= {arXiv preprint arXiv:2110.10973},
year = {2021}
}