A Systematic Survey of Text Worlds as Embodied Natural Language Environments

TL;DR

This paper systematically surveys Text Worlds, virtual textual environments for embodied agents, highlighting recent advancements, challenges, and future directions for leveraging them in natural language processing research.

Contribution

It provides a comprehensive overview of recent developments in tooling, environments, and agent modeling for Text Worlds, emphasizing their potential as a research paradigm.

Findings

Recent trends in knowledge graphs and common sense reasoning.

Transfer learning from Text Worlds to 3D environments.

Development targets for making Text Worlds more versatile.

Abstract

Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D environments, are rendered exclusively using textual descriptions. These environments offer an alternative to higher-fidelity 3D environments due to their low barrier to entry, providing the ability to study semantics, compositional inference, and other high-level tasks with rich high-level action spaces while controlling for perceptual input. This systematic survey outlines recent developments in tooling, environments, and agent modeling for Text Worlds, while examining recent trends in knowledge graphs, common sense reasoning, transfer learning of Text World performance to higher-fidelity environments, as well as near-term development targets that, once achieved, make Text Worlds an attractive general research paradigm for natural language processing.