Skip to content

An OpenAI Gym environment for Inventory Control problems

Notifications You must be signed in to change notification settings

paulhendricks/gym-inventory

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

gym-inventory

The Inventory environment is a single agent domain featuring discrete state and action spaces. Currently, one task is supported:

Simple Inventory Control with Lost Sales

This environment corresponds to the version of the inventory control with lost sales problem described in Example 1.1 in Algorithms for Reinforcement Learning by Csaba Szepesvari (2010).

Future tasks

Future tasks will have more complex environments that take into account:

  • Demand-effecting factors such as trend, seasonality, holidays, weather, etc.
  • Business-specific factors such as lead times, penalties for carrying inventory, etc.
  • Scaling from 1 to millions of SKUs and learning across SKUs.

Installation

cd gym-inventory
pip install -e .

About

An OpenAI Gym environment for Inventory Control problems

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages