Advances in artificial intelligence and optimal control provide increasingly better algorithms for controlling dynamical systems. These algorithms can be applied for policy design in system dynamics models. In this paper we introduce some basic solution concepts and apply the Q-learning algorithm to a simple dynamic model from system dynamics literature to demonstrate potential value of such cross-fertilization. We also extend a state aggregation and partitioning algorithm that may increase the efficiency of basic reinforcement learning models in application to continuous time and space problems. Simulation analysis demonstrates the value of this approach and offers guidelines for future research.

This is the whole item.

Date created

• 2008 July 20-2008 July 24

Type

• Document

Processing Activity

• Processing documentation available at: https://wiki.albany.edu/display/SCA/Processing+Ingested+Digital+Files

License

• Creative Commons BY-NC-ND Attribution-NonCommercial-NoDerivs 4.0 International

  
  Contact Us for questions or additional rights.

ITEM CONTEXT

Part of

6cbae5a21467df4434abbc87da443217

Scope and Contents

Part of

ce498623f0349395d0a141a0525190a0

Scope and Contents

Part of

23d738ba88f8333bc39725f9cb5bd0b8

Scope and Contents

Collection

System Dynamic Society Records

Scope and Contents

Collecting area

• This collection is part of the University Archives