Evolutionary optimisation

The technique

Try many slightly different versions, keep the ones that did best, make the next generation from them, and repeat; no gradient needed.

Read the primer

Approaches using this technique

6 approaches, featured pages first. Each card is one theory of how to choose a column and what happened when it was tried.

Evolutionary optimisationfeatured

An evolved NNUE leaf, distilled from a depth-5 teacher

A compact neural leaf evaluator for the depth-3 fair search, warm-started by distilling a depth-5 teacher's sibling-complete root values and then refined by an evolutionary search whose fitness is whole-game score itself.

rejectedrecorded

Evolutionary optimisationfeatured

Evolution

Let a search tune board-feature weights by playing thousands of games, keeping the best weights, and repeating.

rejectedrecorded

Evolutionary optimisation

Direct public policy

Skip the value model. Score each column with 25 weighted features and tune the weights against whole games.

rejected

Evolutionary optimisation

Evolved public policy

Give the weight search a larger phase-aware evaluator and optimise complete games directly, without imitation or proxy labels.

rejectedrecorded

Evolutionary optimisation

Evolving the leaf weights at the depth they are used

Evolves the reference evaluator on complete games, then tests the frozen winner once on unseen games.

Evolutionary optimisation

Machine-tuning the board evaluator

Let an optimiser adjust eight coefficients of the search's board evaluator by playing complete games, then freeze the winner and test it on games it never saw.

rejectedrecorded

Agent contextApproach directories in this group, by family

fair-expectimax

approaches/fair-expectimax/cem

heuristic-search

lifetime-objective

value-policy-learning

approaches/value-policy-learning/direct-policy