Thinking Fast and Slow in AI: the Role of Metacognition
Summary
Bergamaschi Ganapini et al. propose SOFAI: System 1 solvers answer from experience by default, and a metacognitive agent decides when to call System 2.
SOFAI is System 1 by default.
Incoming tasks go first to constant-time experience-based solvers; System 2 agents never run unless the metacognitive module invokes them.
This is clearly an S1-by-default architecture, analogous to what happens in humans
Models of self, world, and others support both solver kinds.
A background updater keeps past decisions, resource costs, rewards, environment knowledge, and beliefs about other agents current.
Meta-cognition is generally understood as any cognitive process that is about some other cognitive process
MC1 often stops at System 1.
It accepts the fast answer when confidence is high relative to expected reward, or when there are not enough resources for a deeper check.
MC2 pays for System 2 only when the extra expected reward beats expected cost.
It compares the System 1 action's expected value against the cost of running a slower solver.
we do not assume that S2 solvers are always better than S1 solvers
Sequential problems can arbitrate per step or once per plan.
Per-decision metacognition is more flexible; whole-plan solvers can use deeper domain knowledge when metacognition runs once.
Read the original ↗Save to your Sponge
Summarized with Sponge. Quotes are the author’s own words.