A Survey of Text Games for Reinforcement Learning Informed by Natural Language

Philip Osborne, Heido Nõmm, André Freitas


Abstract
Reinforcement Learning has shown success in a number of complex virtual environments. However, many challenges still exist towards solving problems with natural language as a core component. Interactive Fiction Games (or Text Games) are one such problem type that offer a set of safe, partially observable environments where natural language is required as part of the Reinforcement Learning solution. Therefore, this survey’s aim is to assist in the development of new Text Game problem settings and solutions for Reinforcement Learning informed by natural language. Specifically, this survey: 1) introduces the challenges in Text Game Reinforcement Learning problems, 2) outlines the generation tools for rendering Text Games and the subsequent environments generated, and 3) compares the agent architectures currently applied to provide a systematic review of benchmark methodologies and opportunities for future researchers.
Anthology ID:
2022.tacl-1.51
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
873–887
Language:
URL:
https://aclanthology.org/2022.tacl-1.51
DOI:
10.1162/tacl_a_00495
Bibkey:
Cite (ACL):
Philip Osborne, Heido Nõmm, and André Freitas. 2022. A Survey of Text Games for Reinforcement Learning Informed by Natural Language. Transactions of the Association for Computational Linguistics, 10:873–887.
Cite (Informal):
A Survey of Text Games for Reinforcement Learning Informed by Natural Language (Osborne et al., TACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.tacl-1.51.pdf