Watching an AI Learn Tic-Tac-Toe
Your turn — you're X. Click a cell.
New round
Reset AI's knowledge
Train the AI
Learning rate (α)
0.30
How much each game changes what the AI believes. Higher = learns faster but noisier.
Exploration rate (ε)
0.20
How often it tries a random move instead of its best-known one, to discover new strategies.
Games per training batch
100 games
1,000 games
5,000 games
20,000 games
Train batch
What it has learned
Games trained so far
0
Last batch result
X won
O won
Draw
AI's last move
Play settings
Who goes first
Takes effect on the next new round.
You start (you're X)
AI starts (AI is X, you're O)
AI also learns from games played against you (uses α above)
Let the AI explore during play too (uses ε above)