Understanding Conflict with a Socio-Cognitive Computational Approach
	Training Dynamic Decision Making in Mine Emergency Situations
	Hypothesis Generation & Reasoning in Dynamic Cyber SA Decision Making
	Training Decision Making Skills
	Cognitive Process Modeling and Measurement in Dynamic Decision Making
	Hypothesis Generation & Feedback in Dynamic Decision Making
	Learning & Adaptation in Complex Decision Making Situations
	Neural Basis of Decision Making

Former Sponsored Projects

Facilities, Methods, & DMGames

	Facilities & Methods
	DMGames

	Dynamic Climate Change Simulator (DCCS)
	Dynamic Stocks & Flows (DSF)
	The Water Purification Plant (WPP)
	FIRECHIEF
	Beer Game
	MEDIC

Project Researchers: Cleotilde Gonzalez (PI)

Overview

The Instance-Based Learning Theory (IBLT) (Gonzalez, Lerch, & Lebiere, 2003) proposes that in dynamic environments, learning occurs through the accumulation and refinement of decision instances and that decision making is based on the retrieval of solutions stored in similar memory instances. Our experimental results suggest practical ways to facilitate successful supply chain management learning. An example of a dynamic decision making problem used in this project is the Beer Game: a supply chain management task.

The Dynamic Decision Making Laboratory is part of the Social and Decision Sciences Department,  Carnegie Mellon University. For updates and comments, please email hauyuw@andrew.cmu.edu.