# RoboSumo

 [“RoboSumo”](https://github.com/openai/robosumo), virtual humanoid “metalearning” robots initially lack knowledge of how to even walk, and given the goals of learning to move around, and pushing the opposing agent out of the ring. 

![](https://4213617597-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-LqMg4qkOis4QLHkiBUK%2F-LqcUxw9o6yoTK07KQtL%2F-LqcW1kWvozLurLmwf-B%2Fimage.png?alt=media\&token=1cdfa97d-39bb-4b5f-bde7-114dc2c10f3c)

Through this adversarial learning process, the agents learn how to adapt to changing conditions; when an agent is then removed from this virtual environment and placed in a new virtual environment with high winds, the agent braces to remain upright, suggesting it had learned how to balance in a generalized way.