Learning to model other minds
核心要点速览
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.
查看完整报道与分享
完整图文、背景资料与讨论归原始发布平台 OpenAI News 所有。