An early checkers program got better by playing games against itself.
Picture a kid at the kitchen table. He plays both sides of checkers. Each loss is free coaching.
Samuel’s program learned from its own games. It showed early AI could improve through experience, not just fixed moves.
RL
The Samuel Checkers Program learned from wins and losses, like an early form of RL.
Minimax Search
It looked a few moves ahead and compared possible plays.
Game AI
It showed games could be a training ground for AI.
TD-Gammon
TD-Gammon later used the same self-play path for backgammon.