Abstract
How could machines learn as efficiently as humans and animals? How could machines learn to reason and plan? How could machines learn representations of percepts and action plans at multiple levels of abstraction, enabling them to reason, predict, and plan at multiple time horizons? This position paper proposes an architecture and training paradigms with which to construct autonomous intelligent agents. It combines concepts such as configurable predictive world model, behavior driven through intrinsic motivation, and hierarchical joint embedding architectures trained with self-supervised learning.
Meta's Chief AI Scientist Yann Lecun lays out his vision for what an architecture for generally intelligent agents might look like.
I agree. I shared the post on an a couple AI safety Slack and Discord channels just now to try and get it more visibility.