Return to Microsoft Research Lab – Montréal
Language for Learning and Interaction | Montréal
Building interactive language agents that make sense of the world’s information
News & features
Loading…
In the news | SiliconANGLE
Microsoft’s new TextWorld framework generates games to train AI models
TextWorld enables researchers to define how games should play out by providing high-level specifications. It also lets researchers use existing, human-written games to create an even more challenging training environment.
Microsoft Research Blog
TextWorld: A learning environment for training reinforcement learning agents, inspired by text-based games
| Wendy Tay, Adam Trischler, and Emery Fine
Today, fresh out of the Microsoft Research Montreal lab, comes an open-source project called TextWorld. TextWorld is an extensible Python framework for generating text-based games. Reinforcement learning researchers can use TextWorld to train and test AI agents in skills such…