Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents

Shunyu Yao, Karthik Narasimhan, Matthew Hausknecht


Abstract
Text-based games simulate worlds and interact with players using natural language. Recent work has used them as a testbed for autonomous language-understanding agents, with the motivation being that understanding the meanings of words or semantics is a key component of how humans understand, reason, and act in these worlds. However, it remains unclear to what extent artificial agents utilize semantic understanding of the text. To this end, we perform experiments to systematically reduce the amount of semantic information available to a learning agent. Surprisingly, we find that an agent is capable of achieving high scores even in the complete absence of language semantics, indicating that the currently popular experimental setup and models may be poorly designed to understand and leverage game texts. To remedy this deficiency, we propose an inverse dynamics decoder to regularize the representation space and encourage exploration, which shows improved performance on several games including Zork I. We discuss the implications of our findings for designing future agents with stronger semantic understanding.
Anthology ID:
2021.naacl-main.247
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3097–3102
Language:
URL:
https://aclanthology.org/2021.naacl-main.247
DOI:
10.18653/v1/2021.naacl-main.247
Bibkey:
Cite (ACL):
Shunyu Yao, Karthik Narasimhan, and Matthew Hausknecht. 2021. Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3097–3102, Online. Association for Computational Linguistics.
Cite (Informal):
Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents (Yao et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.247.pdf
Video:
 https://aclanthology.org/2021.naacl-main.247.mp4
Data
Jericho