AlphaZero
AlphaZero learns board games by playing against itself many times.
What it does
AlphaZero learns board games by playing against itself many times.
Self-Play: Practicing with yourself • Grandmaster: Top-tier player
How it works
- Start without human game examples.
- Play games against itself.
- Keep the strategies that win more often.
Uses & Applications
- It can learn games like chess or Go.
- Researchers use it to study planning and strategy.
- Game designers can study strong computer play.
In short
AlphaZero improves through self-play.
Try it yourself
Learn a game by playing both sides
Take one or two stones on each turn. Whoever takes the last stone wins. The computer learns from games it plays against itself.
Your turn
Change one setting at a time. Reset example puts everything back.
Inspect self-play experience
Step 1Why this happens