RLBuilderConfigInput

Reinforcement-learning section input (RL Release 2). See RLBuilderConfig.

input RLBuilderConfigInput {
  enabled: Boolean!
  algorithm: String!
  timeframe: String
  trainPeriodDays: Int
  backtestPeriodDays: Int
  identifier: String!
  features: [IndicatorDefinitionInput!]
  reward: RewardExpressionJSON
  modelRewardParameters: Map
  rawRlConfig: Map
}

Fields

RLBuilderConfigInput.enabled ● Boolean! non-null scalar

RLBuilderConfigInput.algorithm ● String! non-null scalar

The sb3/sb3-contrib algorithm class name (validated against rlAlgorithmCatalogue, e.g. "PPO").

RLBuilderConfigInput.timeframe ● String scalar

RLBuilderConfigInput.trainPeriodDays ● Int scalar

RLBuilderConfigInput.backtestPeriodDays ● Int scalar

RLBuilderConfigInput.identifier ● String! non-null scalar

RLBuilderConfigInput.features ● [IndicatorDefinitionInput!] list input

Feature nodes — reuses the IndicatorDefinitionInput vocabulary. Empty falls back to the scaffold's baseline feature set.

RLBuilderConfigInput.reward ● RewardExpressionJSON scalar

Optional reward-expression tree (RL Release 2 SP2). Closed whitelisted numeric vocabulary; absent/invalid → scaffold default reward.

RLBuilderConfigInput.modelRewardParameters ● Map scalar

RLBuilderConfigInput.rawRlConfig ● Map scalar

Member Of

UIBuilderConfigInput input