GitHub · Jupyter Notebook
microsoft/TextWorld
TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.
- Stars
- 1,467
- Forks
- 210
- Stars gained in 24 hours
- +12
- Forks gained in 24 hours
- +2
Topics: reinforcement-learning, text-based-adventure, text-based-game
Latest data point: Nov 22, 2026 · 1,467 stars · 210 forks