pg.evolution.neat

Accessible via pg.evolution.neat.

neat(mutator=Uniform(where=None, seed=None), population_size=100, disjoint_coefficient=1.0, matching_coefficient=3.0, compatibility_threshold=0.4, remaining_ratio=0.6, seed=None)[source]

NEAT Algorithm.

See http://nn.cs.utexas.edu/downloads/papers/stanley.cec02.pdf for the original paper.

NOTE(daiyip): PyGlove supports search spaces that do not change during exploration. Therefore we do not grow the program (e.g. Neural Architecture in the paper) from a minimal program. Also, crossover can take place on any two individuals due to a fixed program structure, which will be implemented later. This algorithm illustrates how speciation is expressed in the compositional evolution framework.

Return type:

pg.evolution.Evolution

Parameters:

  • mutator – Mutator to use.

  • population_size – Population size for each generation.

  • disjoint_coefficient – Coefficient for DNA disjointness. Used for distance computations.

  • matching_coefficient – Coefficient for DNA matching. Used for distance computations.

  • compatibility_threshold – Threshold for max distances between two DNA in the same species.

  • remaining_ratio – Ratio of best individuals in a species to remain.

  • seed – Random seed. If None, use the current system time.

Returns:

An Evolution object that represents the NEAT algorithm.