pulumi-azure-native-kotlin/com.pulumi.azurenative.machinelearningservices.kotlin.inputs/BanditPolicyArgs

BanditPolicyArgs

data class BanditPolicyArgs(val delayEvaluation: Output<Int>? = null, val evaluationInterval: Output<Int>? = null, val policyType: Output<String>, val slackAmount: Output<Double>? = null, val slackFactor: Output<Double>? = null) : ConvertibleToJava<BanditPolicyArgs>

Defines an early termination policy based on slack criteria, and a frequency and delay interval for evaluation

Constructors

Link copied to clipboard
fun BanditPolicyArgs(delayEvaluation: Output<Int>? = null, evaluationInterval: Output<Int>? = null, policyType: Output<String>, slackAmount: Output<Double>? = null, slackFactor: Output<Double>? = null)

Functions

Link copied to clipboard
open override fun toJava(): BanditPolicyArgs

Properties

Link copied to clipboard
val delayEvaluation: Output<Int>? = null

Number of intervals by which to delay the first evaluation.

Link copied to clipboard
val evaluationInterval: Output<Int>? = null

Interval (number of runs) between policy evaluations.

Link copied to clipboard
val policyType: Output<String>

Expected value is 'Bandit'.

Link copied to clipboard
val slackAmount: Output<Double>? = null

Absolute distance allowed from the best performing run.

Link copied to clipboard
val slackFactor: Output<Double>? = null

Ratio of the allowed distance from the best performing run.