factual
Restless Bandit Problem Reflects Changing Environments
Real environments drift, so the restless bandit variant, where reward probabilities random-walk over time, is theoretically unsettled, yet humans in lab studies handle it without trouble, suggesting cognitive scientists have models that mathematicians could learn from.
factualpending
Speaker
BrianEvidence Quote
“if you put people in a lab and give them a restless bandit problem, they have no trouble making choices within that environment. But we don't yet know what the mathematics of the optimal solution looks like.”
Created: 11/19/2026, 9:46:21 AM
Your notes
Loading notes...