ribs.emitters

Emitters output new candidate solutions in QD algorithms.

A note on data types: The emitters provided here will use the same data type as the ones in the archive passed in.

ribs.emitters.GaussianEmitter(archive, x0, …)

Emits solutions by adding Gaussian noise to existing archive solutions.

ribs.emitters.IsoLineEmitter(archive, x0[, …])

Emits solutions that are nudged towards other archive solutions.

ribs.emitters.ImprovementEmitter(archive, …)

Adapts a covariance matrix towards changes in the archive.

ribs.emitters.RandomDirectionEmitter(…[, …])

Performs a random walk in behavior space by pursuing randomly chosen behavior space directions.

ribs.emitters.OptimizingEmitter(archive, x0, …)

Adapts a covariance matrix towards the objective.

ribs.emitters.EmitterBase(archive, …[, seed])

Base class for emitters.