com.eignex.kumulant/bandit/univariate/Greedy

Greedy

class Greedy(priorMean: Double = 0.0, priorWeight: Double = 0.02, priorSquaredDeviations: Double = 0.02) : BanditPolicy<WeightedVarianceResult> (source)

Pure-exploitation policy: always picks the arm with the highest posterior mean. No exploration at all; converges fastest to the apparent best arm but can lock into a suboptimal arm forever if early rewards mislead it.

Useful as a baseline (regret comparison against random / UCB / Thompson) and as a quick-and-dirty starting policy when prior beliefs are already good. For real online learning use one of the exploration-bearing policies instead.

Constructors

Greedy

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

Properties

arm

open override val arm: NormalArm(source)

Per-arm cumulator spec; determines the prior pseudo-counts, value encoding, and result shape that evaluate consumes.

Functions

evaluate

open override fun evaluate(snapshot: WeightedVarianceResult, step: Long, rng: Random): Double(source)

Score an arm given its current snapshot. Higher scores are preferred by the bandit. step is the global update count (for time-dependent exploration schedules); rng is the bandit's shared com.eignex.kumulant.bandit.Bandit.random (consumed by sampling policies).

addArm

open fun addArm(snapshot: WeightedVarianceResult)

Hook called when a new arm joins the population. Lets stateful policies fold the new arm's snapshot into their global counters (UCB's total-samples, UCB1Normal's arm count). Default no-op.

createArm

open fun createArm(): SeriesStat<WeightedVarianceResult>

Allocate a fresh per-arm accumulator from the arm spec. Default delegates to arm.createStat(); override only if the policy needs a non-standard variant.

removeArm

open fun removeArm(snapshot: WeightedVarianceResult)

Hook called when an arm leaves the population. Inverse of addArm; lets stateful policies remove the departing arm's contribution from their global counters. Default no-op.

update

open fun update(stat: SeriesStat<WeightedVarianceResult>, value: Double, weight: Double = 1.0)

Fold an observed reward value (with optional weight) into the per-arm stat. Default applies arm.encode first; policies with global counters (UCB families) override to update their counter alongside the stat update.