kumulant

Ucb1TunedSpec

@Serializable
@SerialName(value = "UCB1Tuned")
data class Ucb1TunedSpec(val alpha: Double = 1.0, val priorMean: Double = 0.0, val priorWeight: Double = 0.02) : BanditPolicySpec<MomentsResult> (source)

Spec for UCB1Tuned.

Constructors

Ucb1TunedSpec

constructor(alpha: Double = 1.0, priorMean: Double = 0.0, priorWeight: Double = 0.02)(source)

Properties

alpha

Exploration scale on the confidence-bound term.

priorMean

Per-arm prior on the running reward mean.

priorWeight

Per-arm prior pseudo-count.