Namespace OptunaSharp.Samplers.EvolutionStrategy

Classes

EvolutionStrategySampler

Base class for the Evolution-Strategy samplers. Drives an OptunaSharp.Samplers.EvolutionStrategy.IEvolutionStrategyOptimizer through the Optuna study protocol the way CmaEsSampler drives Cma: continuous Float/Int parameters form a relative search space; the population is spread across consecutive trials; and the optimizer state round-trips through trial system attrs (own JSON, chunked to the storage string-length limit) so a study resumes across process boundaries and distributed workers.

Categorical parameters, single-valued distributions, and the first nStartupTrials trials are handled by the independent sampler, exactly as in CmaEsSampler. Dynamic search spaces are unsupported (the sampler falls back to independent sampling with a warning).