The Alberta Plan for AI Research: Continual Reinforcement Learning
Professor of Computing Science & Turing Laureate, University of Alberta
Outlines a roadmap for continual, agent-centric intelligence built from online temporal-difference prediction, meta-step-size adaptation, and learned predictive world models.
Artificial general intelligence (AGI) is one of the grand ambitions of much machine learning research — the benefits of an artificial intelligence agent that can learn and understand tasks at a near-human level could transform the world as we know it. It would be one of the greatest scientific achievements of all time, argues Amii Fellow, Canada CIFAR AI Chair & Chief Scientific Advisor Rich Sutton, and will happen sooner than we might think.
Watch Sutton lay out the Alberta Plan - a twelve-stage roadmap that he things could lead to a fuller understanding of intelligence.