SimEd: simulating education as a multi agent system

This paper describes our efforts in creating SimEd, a simulation of the education system. The longterm aim of this work is to be able to model the types of interactions and interplays that occur between students, teachers and administrators, resulting in a toolkit and a methodology that will allow policy makers on various levels to experiment with their decisions, examining effects over time and across levels. Here, we outline our reasoning for selecting the multi agent system paradigm and the particular techniques chosen. We present details of two components within the SimEd toolkit and show results of experimental simulations executed with each. In constructing these tools, we have begun to identify special attributes of the education environment that set it aside from more typical agent-based application areas, such as e-commerce. We highlight these aspects and discuss current and future work extending agent techniques to accommodate these types of environments.

[1]  W. Lewis Johnson,et al.  Integrating pedagogical capabilities in a virtual environment agent , 1997, AGENTS '97.

[2]  John Seely Brown,et al.  Diagnostic Models for Procedural Bugs in Basic Mathematical Skills , 1978, Cogn. Sci..

[3]  George W. Bohrnstedt,et al.  What We Have Learned about Class Size Reduction in California. Capstone Report. , 2002 .

[4]  Kurt VanLehn,et al.  Student Modeling from Conversational Test Data: A Bayesian Approach Without Priors , 1998, Intelligent Tutoring Systems.

[5]  James C. Lester,et al.  Mixed Initiative Problem Solving with Animated Pedagogical Agents , 1997 .

[6]  Elizabeth Sklar,et al.  Towards the application of argumentation-based dialogues for education , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[7]  John R. Anderson.  Acquisition of cognitive skill. , 1982 .

[8]  Frederick Mosteller,et al.  The Tennessee Study of Class Size in the Early School Grades , 1997 .

[9]  Daniel F. McCaffrey,et al.  What We Have Learned About Class Size Reduction in California , 2002 .

[10]  Charles M. Achilles,et al.  Class Size: Counting Students Can Count , 2003 .

[11]  Wendy Schwartz.  Class Size Reduction and Urban Students. ERIC Digest. , 2003 .

[12]  Elizabeth Sklar,et al.  Modeling Human Learning as a Cooperative Multi Agent Interaction , 2003 .

[13]  Jordan B. Pollack,et al.  Co-Evolution in the Successful Learning of Backgammon Strategy , 1998, Machine Learning.

[14]  Marc Esteva,et al.  On the formal specification of electronic institutions , 2001 .

[15]  Elizabeth Sklar,et al.  Co-evolutionary Learning : Machines and Humans Schooling Together , 1998 .

[16]  Robert Axelrod.  Advancing the art of simulation in the social sciences , 1997 .

[17]  Marc Esteva,et al.  ISLANDER: an electronic institutions editor , 2002, AAMAS '02.

[18]  W. Hamilton,et al.  The evolution of cooperation. , 1984, Science.

[19]  W. Lewis Johnson,et al.  Pedagogical agents on the Web , 1999, AGENTS '99.

[20]  F. Dignum,et al.  Agent Mediated Electronic Commerce: The European AgentLink Perspective , 2001 .

[21]  Marc Esteva,et al.  On the Formal Specifications of Electronic Institutions , 2001, AgentLink.

[22]  Joseph Krajcik,et al.  The design of guided learner-adaptable scaffolding in interactive learning environments , 1996, CHI.

[23]  J. Forrester.  System Dynamics and the Lessons of 35 Years , 1993 .

[24]  D. Cliff.  Minimal-Intelligence Agents for Bargaining Behaviors in Market-Based Environments , 1997 .

[25]  William J. Clancey.  Intelligent Tutoring Systerns: A Tutorial Survey , 1986 .

[26]  Roger C. Schank,et al.  Engines for Education , 1995 .

[27]  Hiroaki Kitano,et al.  The RoboCup Synthetic Agent Challenge 97 , 1997, IJCAI.