Learning to model other minds
We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s dilemma. This algorithm, Learning with Opponent-Learning Awareness (LOLA), is a small step towards agents that model other minds.
Source — openai-blog
Read Full Article
Published: Thu, 14 Sep 2017 07:00:00 GMT
Category — AI
Region: openai-blog | Section: AI
Related: ai • openai-blog