A Systematic Survey of Text Worlds as Embodied Natural Language Environments

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 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.

ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games

“…Text Games and Virtual Environments: Interactive text environments are an attractive choice for studying embodied agents, owing to their relative simplicity compared to full 3D simulations and ability to model complex and abstract tasks (Jansen, 2021;Li et al, 2021). While early text game research focused on testing agents on a small set of extant "interactive fiction" games like Zork, recent approaches have leaned towards procedurally generating a wider set of simple text-based games in order to evaluate agents' ability to generalize (Côté et al, 2018;Shridhar et al, 2020;Wang et al, 2022).…”