Neuro-Symbolic Approaches for Text-Based Policy Learning
Subhajit Chaudhury, Prithviraj Sen, Masaki Ono, Daiki Kimura, Michiaki Tatsubori, Asim Munawar
Abstract
Text-Based Games (TBGs) have emerged as important testbeds for reinforcement learning (RL) in the natural language domain. Previous methods using LSTM-based action policies are uninterpretable and often overfit the training games showing poor performance to unseen test games. We present SymboLic Action policy for Textual Environments (SLATE), that learns interpretable action policy rules from symbolic abstractions of textual observations for improved generalization. We outline a method for end-to-end differentiable symbolic rule learning and show that such symbolic policies outperform previous state-of-the-art methods in text-based RL for the coin collector environment from 5-10x fewer training games. Additionally, our method provides human-understandable policy rules that can be readily verified for their logical consistency and can be easily debugged.
BibTeX
@inproceedings{chaudhury-etal-2021-neuro,
title = "Neuro-Symbolic Approaches for Text-Based Policy Learning",
author = "Chaudhury, Subhajit and
Sen, Prithviraj and
Ono, Masaki and
Kimura, Daiki and
Tatsubori, Michiaki and
Munawar, Asim",
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.245/",
doi = "10.18653/v1/2021.emnlp-main.245",
pages = "3073--3078"
}