CM / QUANApplied intelligence · Reinforcement learningFIELDNOTES / 2026

Curious Machine / Interactive lab

The long way home.

An agent can know the shortest route and still choose a safer one. Explore planning, learning and the cost of a wrong step.

Download evidence ↗

Swipe the table sideways to see all columns.

01 / Method

What was actually measured.

02 / Boundaries

What this does not prove.