shipfeedAI news, curated daily

01:15:49 CET
21 MAY01:15:49shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Learning to model other minds

DeepMind releases LOLA, a multi-agent learning algorithm that accounts for other agents' learning dynamics and discovers collaborative strategies such as tit-for-tat in iterated games.

Sep 14 · · primary fetch1 sourceupdated Sep 14 ·

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.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comLearning to model other mindsprimary