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

TL;DR

This survey reviews the challenges, tools, and agent architectures in Text Game Reinforcement Learning, aiming to guide future research in natural language-based virtual environments.

Contribution

It provides a comprehensive overview of challenges, evaluation tools, and agent architectures in Text Game RL, highlighting opportunities for future advancements.

Findings

Identifies key challenges in Text Game RL environments.

Summarizes tools for generating and evaluating Text Games.

Compares current agent architectures and benchmark methods.

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 partially observable environments where natural language is required as part of the reinforcement learning solutions. 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 summarises: 1) the challenges introduced in Text Game Reinforcement Learning problems, 2) the generation tools for evaluating Text Games and the subsequent environments generated and, 3) the agent architectures currently applied are compared to provide a systematic review of benchmark methodologies and opportunities for future researchers.