liveBook · Manning

Setup cost

As explained in Applied Reinforcement Learning

A setup cost is the expense incurred when configuring or switching production equipment for a product.

In production planning, a setup cost is the penalty for switching equipment from one product to another. A $200 switching penalty lowers the reward, discouraging changes unless switching is worthwhile. section 2.5

Listing 2.4 Factory problem definition
Class FactoryProblemDefinition:
    lambda_scooter = 4.0 #A
    lambda_bike = 3.0 #A
    horizon = 30   #A
 
    prod_capacity_scooter = 8 #B
    prod_capacity_bike = 6 #B
 
    price_scooter = 40.0 #C
    price_bike = 50.0 #C
    cost_scooter = 20.0  #C
    cost_bike = 25.0  #C
 
    setup_cost = 200.0    #D
    holding_cost = 2.0    #D
    backorder_cost = 10.0 #D

The factory configuration sets setup cost to $200 alongside holding and backorder costs. section 2.5

How Applied Reinforcement Learning covers it

How deep it goes
Defines the switching penalty and shows it applied when production changes from the current setup.
Examples
Uses a $200 penalty for switching a factory line between scooters and bikes.
What you can do after
Understand how a switching penalty affects production rewards and encourages staying with the current product.
How it connects
Connects setup cost to reward functions, production cost, holding cost, and backorder penalties.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Applied Reinforcement Learning. The section links point to the parts of the book it draws on.