RL 4: Early heuristics and the birth of Temporal Difference learning (1959–1968)

Automated excerpt

That's model-free learning, and it turns out to be the exact same rule psychologists later used to explain Pavlov's dogs. The machine wasn't just learning checkers — it was learning what was worth paying attention to. Michie didn't load every box with the same number of beads.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.