actionrwd.demand(..) 🡒 ranvar, process

The function returns a ranvar that represents the probabilistic cumulative demand, period per period, as obtained from the underlying demand generator used for the action reward function. The function actionrwd.demand() is intended as a support function for actionrwd.reward() to visualize the demand trajectories internally used by the action reward function.

table P = extend.range(20)

P.D = actionrwd.demand(
  TimeIndex: P.N
  BaseLine: P.5
  Dispersion: 1.0
  Alpha: 0.3)

show plot "Cumulative trajectories" a1e5 with
  quantile(P.D, 0.90) as "Q95" { color: red }
  mean(P.D) as "Avg"
  quantile(P.D, 0.10) as "Q05" { color: blue }

See actionrwd.reward.

Function signature

/// Returns a ranvar that represents the cumulative demand
/// associated to the trajectories as generated by 'actionrwd.reward'.
call actionrwd.demand<Items, Periods>(
    /// Time index of the period. Links the table to the time. Starts at one.
    Periods.TimeIndex: number as "TimeIndex",
    /// The baseline of the average demand over each period.
    Periods.Baseline: number as "Baseline",
    /// The dispersion parameter (variance divided by mean) of the demand for each item.
    Items.Dispersion: number as "Dispersion",
    /// The update speed parameter of the ISSM model for each item.
    Items.Alpha: number as "Alpha",
    /// Number of trajectories used to evaluate the cumulative demand.
    /// The parameter has to be defined within [1, 10'000]. Default: 2'500.
    scalar.Samples?: number as "Samples",  
    /// Seed used for the trajectory generator.
    scalar.Seed?: number as "Seed",
    Items -> Periods) : Periods.ranvar as "actionrwd.demand"
User Contributed Notes
0 notes + add a note