← All Cracked ML projects
PL-A09NOT STARTEDADVANCEDMLPYTHONIMPACT ★★★☆☆

AlphaZero Connect-4, graded by a perfect solver

Connect-4 is solved, so every move your self-play agent makes can be marked right or wrong.

EST.35 h
REWARD+400 XP
AFTERSilver et al. + 1

ML-ARENA BENCHMARKS

PROOF: BENCH
METRICINDUSTRYMINE
% optimal moves on 1,000 solver-labelled positions; win rate as first player vs the solver; GPU-hours used
GOAL · ≥ 95% optimal moves; ≥ 90% wins as first player vs perfect play; ≤ 24 GPU-hours of self-play
Pascal Pons's Connect-4 perfect solver (ground truth)—
no results yet
YOUR RESULTS

Your recorded results appear here.

Brief

Build PUCT MCTS with batched neural evaluation. MCTS (Monte Carlo tree search) plans by simulating many possible continuations; PUCT is the AlphaZero rule that uses the network's move probabilities and value estimates to choose which branches to explore. Add a small ResNet policy/value net (one head suggests moves, the other predicts who will win), self-play workers, a replay buffer (a store of recent self-play positions to train on) and an arena-gated training loop (a new network replaces the current one only if it wins a head-to-head match). Grade the agent with Pascal Pons's solver: the share of optimal moves on random mid-game positions, and games played as first player (a forced win under perfect play).

VICTORY CONDITIONS

  1. ≥ 95% optimal moves; ≥ 90% wins as first player vs perfect play; ≤ 24 GPU-hours of self-play (% optimal moves on 1,000 solver-labelled positions; win rate as first player vs the solver; GPU-hours used).
  2. A public repository with a README that shows your result and how to reproduce it.

Terms in plain words

AlphaZero
A method that learns a game purely by playing itself, combining tree search with a neural network that guides it.
MCTS
Monte Carlo tree search: build a tree of possible moves by repeatedly simulating games from the current position.
PUCT
The selection rule inside AlphaZero's search that balances the network's suggested moves against moves that are still unexplored.
Policy / value net
One network with two outputs: a probability for each move, and an estimate of who will win.
Arena gating
Only promoting a newly trained network if it beats the current best one in a match.
Solved game
A game where the perfect move in every position is known, so any agent's play can be checked exactly.

Why it rates ★★★☆☆

A complete AlphaZero loop graded by ground truth is far more convincing than reward curves from CartPole.