Research

Learning to model other minds

Source: OpenAI News 14 Sep 2017

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

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.

Why It Matters

Ia langkah awal ke arah agen AI yang mampu memodelkan niat dan pembelajaran pihak lain untuk interaksi strategik lebih baik.

Keep Reading on NadiAI

Selected Related Articles