A Survey of Text Games for Reinforcement Learning Informed by Natural Language
AbstractReinforcement 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...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
The MIT Press
2022-01-01
|
Series: | Transactions of the Association for Computational Linguistics |
Online Access: | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00495/112801/A-Survey-of-Text-Games-for-Reinforcement-Learning |
_version_ | 1798045550494351360 |
---|---|
author | Philip Osborne Heido Nõmm André Freitas |
author_facet | Philip Osborne Heido Nõmm André Freitas |
author_sort | Philip Osborne |
collection | DOAJ |
description |
AbstractReinforcement 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. |
first_indexed | 2024-04-11T23:22:45Z |
format | Article |
id | doaj.art-fe94cf8c18854052abd3f268e600790a |
institution | Directory Open Access Journal |
issn | 2307-387X |
language | English |
last_indexed | 2024-04-11T23:22:45Z |
publishDate | 2022-01-01 |
publisher | The MIT Press |
record_format | Article |
series | Transactions of the Association for Computational Linguistics |
spelling | doaj.art-fe94cf8c18854052abd3f268e600790a2022-12-22T03:57:25ZengThe MIT PressTransactions of the Association for Computational Linguistics2307-387X2022-01-011087388710.1162/tacl_a_00495A Survey of Text Games for Reinforcement Learning Informed by Natural LanguagePhilip Osborne0Heido Nõmm1André Freitas2Department of Computer Science, University of Manchester, United Kingdom. philiposbornedata@gmail.comDepartment of Computer Science, University of Manchester, United Kingdom. heidonomm@gmail.comDepartment of Computer Science, University of Manchester, United Kingdom. andre.freitas@manchester.ac.uk AbstractReinforcement 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.https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00495/112801/A-Survey-of-Text-Games-for-Reinforcement-Learning |
spellingShingle | Philip Osborne Heido Nõmm André Freitas A Survey of Text Games for Reinforcement Learning Informed by Natural Language Transactions of the Association for Computational Linguistics |
title | A Survey of Text Games for Reinforcement Learning Informed by Natural Language |
title_full | A Survey of Text Games for Reinforcement Learning Informed by Natural Language |
title_fullStr | A Survey of Text Games for Reinforcement Learning Informed by Natural Language |
title_full_unstemmed | A Survey of Text Games for Reinforcement Learning Informed by Natural Language |
title_short | A Survey of Text Games for Reinforcement Learning Informed by Natural Language |
title_sort | survey of text games for reinforcement learning informed by natural language |
url | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00495/112801/A-Survey-of-Text-Games-for-Reinforcement-Learning |
work_keys_str_mv | AT philiposborne asurveyoftextgamesforreinforcementlearninginformedbynaturallanguage AT heidonomm asurveyoftextgamesforreinforcementlearninginformedbynaturallanguage AT andrefreitas asurveyoftextgamesforreinforcementlearninginformedbynaturallanguage AT philiposborne surveyoftextgamesforreinforcementlearninginformedbynaturallanguage AT heidonomm surveyoftextgamesforreinforcementlearninginformedbynaturallanguage AT andrefreitas surveyoftextgamesforreinforcementlearninginformedbynaturallanguage |