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.
Anthology ID:
2021.emnlp-main.245
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3073–3078
Language:
URL:
https://aclanthology.org/2021.emnlp-main.245
DOI:
10.18653/v1/2021.emnlp-main.245
Bibkey:
Cite (ACL):
Subhajit Chaudhury, Prithviraj Sen, Masaki Ono, Daiki Kimura, Michiaki Tatsubori, and Asim Munawar. 2021. Neuro-Symbolic Approaches for Text-Based Policy Learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3073–3078, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Neuro-Symbolic Approaches for Text-Based Policy Learning (Chaudhury et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.245.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.245.mp4
Code
 subhajit1411/slate-text-based-rl