During the 60s and 70s, AI researchers explored intuitions about intelligence by writing programs that displayed intelligent behavior. Many good ideas came out from this work but programs written by hand were not robust or general.
After the 80s, research increasingly shifted to the development of learners
capable of inferring behavior and functions from experience and data,
and solvers capable of tackling well-defined but intractable models like SAT,
classical planning, Bayesian networks, and POMDPs. The learning approach has
achieved considerable success but results in black boxes that do not have the
flexibility, transparency, and generality of their model-based counterparts.
Model-based approaches, on the other hand, require models and scalable algorithms.
In this talk, I review developments in AI, discuss the gap between model-free
learners and model-based solvers, and sketch some of our own recent research
aimed at closing this gap.
Some references:
Model-free, Model-based, and General Intelligence. Hector Geffner.
Proc. IJCAI 2018. https://arxiv.org/abs/1806.02308
Learning Features and Abstract Actions for Computing Generalized Plans
B. Bonet, G. Frances, H. Geffner. Proc. AAAI 2019.
https://arxiv.org/abs/1811.07231