factual

Brain combines model-free RL and model-based reward prediction

The brain layers multiple RL schemes: the striatum/basal ganglia perform simple model-free RL over a finite action space; dopamine carries a reward prediction error signal (per Peter Dayan) consistent with learning value functions; and the cortex builds a model-based world model that predicts when rewards occur, and via RL-as-inference can clamp reward high and sample plans likely to achieve it.

factualpending

Speaker

Adam Marblestone

Evidence Quote

“There's a lot of neuroscience evidence that the dopamine is giving this reward prediction error signal, rather than just reward... that's consistent with learning these value functions.”

Source

Adam Marblestone – AI is missing something fundamental about the brain— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:32:22 AM

Your notes

Loading notes...