woctezuma/puissance4

AI for the game "Connect Four". Available on PyPI.

44
/ 100
Emerging

Implements three progressively sophisticated AI opponents using Monte Carlo tree search: biased random player with game-specific heuristics (winning/blocking moves), pure Monte Carlo evaluation via fixed simulations, and UCT (Upper Confidence bounds for Trees) algorithm balancing exploration-exploitation through the UCB formula with backpropagation. Includes interactive gameplay and batch training modes to benchmark different player strategies across multiple games.

Available on PyPI.

No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 18 / 25
Community 12 / 25

How are scores calculated?

Stars

5

Forks

1

Language

Python

License

MIT

Last pushed

Nov 20, 2025

Monthly downloads

67

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/woctezuma/puissance4"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.