Microsoft Research announces TextWorld, an extensible framework for generating text-based games

Microsoft Research Montreal lab last week announced an open-source project called TextWorld. TextWorld is an extensible framework based on Python which can be used for generating text-based games. Researchers can use this framework to train and test AI agents in skills such as language understanding, memory and planning and more. TextWorld also runs existing text-based games like Zork, for evaluating how well AI agents perform in complex settings.

TextWorld has two main components: a game generator and a game engine. The game generator converts high-level game specifications, such as number of rooms, number of objects, game length, and winning conditions, into an executable game source code in the Inform 7 language. The game engine is a simple inference machine that ensures that each step of the generated game is valid by using simple algorithms such as one-step forward and backward chaining.

“One reason I’m excited about TextWorld is the way it combines reinforcement learning with natural language,” said Geoff Gordon, Principal Research Manager at Microsoft Research Montreal. Learn more about this project from the source link below.

Source: Microsoft