About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Publication
IJCAI 2023
Workshop paper
AI Driven Automation for "Classical" MDP
Abstract
We consider the problem of application of "classical" Markov Decision Process (MDP) to medium-size problems such as waste-water treatment plants and multi-echelon supply chain. These problems consists of dozens to hundreds of state variables and suffer from the "curse of dimensionality". Furthermore, these variables, especially continuous ones, require binning which is time consuming. We show how AI provides automation that lets the LP based MDP algorithm to be useful for solving real-life problems.