kumulant

BoltzmannSpec

@Serializable
@SerialName(value = "Boltzmann")
data class BoltzmannSpec(val nbrArms: Int, val priorMean: Double = 0.0, val priorWeight: Double = 0.02, val initialTau: Double = 1.0, val minTau: Double = 0.001, val decay: Double = 1.0) : UnivariateBanditSpec(source)

Spec for BoltzmannBandit.

Constructors

Link copied to clipboard
constructor(nbrArms: Int, priorMean: Double = 0.0, priorWeight: Double = 0.02, initialTau: Double = 1.0, minTau: Double = 0.001, decay: Double = 1.0)

Properties

Link copied to clipboard

Cooling decay exponent: tau(t) = initialTau / t^decay.

Link copied to clipboard

Initial softmax temperature.

Link copied to clipboard

Floor on the temperature schedule.

Link copied to clipboard

Number of arms in the population.

Link copied to clipboard

Per-arm prior on the running reward mean.

Link copied to clipboard

Per-arm prior pseudo-count.

Functions

Link copied to clipboard
fun BoltzmannSpec.materialize(random: Random = Random.Default): BoltzmannBandit

Build a live BoltzmannBandit from its spec.

fun UnivariateBanditSpec.materialize(random: Random = Random.Default): Bandit

Dispatch any UnivariateBanditSpec to its concrete bandit.

BoltzmannSpec

constructor(nbrArms: Int, priorMean: Double = 0.0, priorWeight: Double = 0.02, initialTau: Double = 1.0, minTau: Double = 0.001, decay: Double = 1.0)(source)

decay

Cooling decay exponent: tau(t) = initialTau / t^decay.

initialTau

Initial softmax temperature.

minTau

Floor on the temperature schedule.

nbrArms

Number of arms in the population.

priorMean

Per-arm prior on the running reward mean.

priorWeight

Per-arm prior pseudo-count.