OpenAI Blog

Learning to model other minds

Read the original on OpenAI Blog →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.

arXiv AI
Aug 3

Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning

arXiv:2511. 22226v2 Announce Type: replace Abstract: The standard theory of model-free reinforcement learning assumes that the environment dynamics are stationary and that agents are decoupled from their environment, such that policies are treated as being separate from the world they inhabit.

By Alexander Meulemans, Rajai Nasser, Maciej Wo{\l}czyk, Marissa A. Weis, Seijin Kobayashi, Blake Richards, Guillaume Lajoie, Angelika Steger, Marcus Hutter, James Manyika, Rif A. Saurous, Jo\~ao Sacramento, Blaise Ag\"uera y Arcas
OpenAI Blog
Jul 4, 2018

Learning Montezuma’s Revenge from a single demonstration

We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human demonstration, better than any previously published result. Our algorithm is simple: the agent plays a sequence of games starting from carefully chosen states from the demonstration, and learns from them by optimizing the game score using PPO, the same reinforcement learning algorithm that underpins OpenAI Five.