4/22/2022: Model-free, Model-based, and General Intelligence: Learning Representations for Acting and Planning, Hector Geffner, ICREA & Universitat Pompeu Fabra, Barcelona, Spain

During the 60s and 70s, AI researchers explored intuitions about intelligence by writing programs that displayed intelligent behavior. Many good ideas came out of 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. The two have close parallels with Kahneman’s Systems 1 and 2: the first, a fast, opaque, and inflexible intuitive mind; the second, a slow, transparent, and flexible analytical mind.

In this talk, I review learners and solvers, and the challenge of integrating their System 1 and System 2 capabilities, focusing then on our recent work aimed at bridging this gap in the context of action and planning, where combinatorial and deep learning approaches are used to learn general action models, general policies, and general subgoal structures.

The presentation recording can be found here.

References:

Model-free, model-based, and general intelligence. Hector Geffner.
IJCAI 2018. https://arxiv.org/abs/1806.02308
Target languages (vs. inductive Biases) for learning to act and plan
Hector Geffner. AAAI 2022. https://arxiv.org/abs/2109.07195