A virtual robot arm has learned to solve a wide range of different puzzles—stacking blocks, setting the table, arranging chess pieces—without having to be retrained for each task. It did this by playing against a second robot arm that was trained to give it harder and harder challenges. Self play: Developed by researchers at OpenAI,…
This is a companion discussion for the article “These virtual robot arms get smarter by training each other - https://www.technologyreview.com/2021/01/22/1016633/robot-arms-smarter-self-play-reinforcement-learning-training-openai/” submitted on the community's news feed.
Reply to this topic to share your thoughts on this article.