OpenAI Blog · Sep 14, 2017
Learning to model other minds
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
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. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Learning to model other minds' affects your current setup before relying on it in production.