This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Graph-Based Analysis of Human Transfer Learning Using a Game Testbed
November 2007 (vol. 19 no. 11)
pp. 1465-1478
The ability to transfer knowledge learned in one environment in order to improve performance in a different environment is one of the hallmarks of human intelligence. Insights into human transfer learning help us to design computer-based agents that can better adapt to new environments without the need for substantial reprogramming. In this paper we study the transfer of knowledge by humans playing various scenarios in a graphically realistic urban setting which are specifically designed to test various levels of transfer. We determine the amount and type of transfer that is being performed based on the performance of human trained and untrained players. In addition, we use a graph-based relational learning algorithm to extract patterns from player graphs. These analyses reveal that indeed humans are transferring knowledge from one set of games to another and the amount and type of transfer varies according to player experience and scenario complexity. The results of this analysis help us understand the nature of human transfer in such environments and shed light on how we might endow computer-based agents with similar capabilities. The game simulator and human data collection also represent a significant testbed in which other AI capabilities can be tested and compared to human performance.

[1] M. Asadi, V. Papudesi, and M. Huber, “Learning Skill and Representation Hierarchies for Effective Control Knowledge Transfer,” Proc. Int'l Conf. Machine Learning (ICML) Workshop Structural Knowledge Transfer for Machine Learning, 2006.
[2] S. Barnett and S. Ceci, “When and Where Do We Apply What We Learn? A Taxonomy for Far Transfer,” Psychological Bull., vol. 128, no. 4, pp. 612-637, 2002.
[3] S. Ben-David and R. Schuller, “Exploiting Task Relatedness for Multiple Task Learning,” Proc. 16th Ann. Conf. Learning Theory (COLT '03), pp. 567-580, 2003.
[4] R. Bjork and A. Richardson-Klavhen, “On the Puzzling Relationship between Environment Context and Human Memory,” Current Issues in Cognitive Processes: The Tulane Flowerree Symposium on Cognition, Elrbaum, 1989.
[5] How People Learn: Brain, Mind, Experience, and School, J. Bransford, A. Brown, and R. Cocking, eds. The Nat'l Academy of Sciences, 1999.
[6] J. Byrnes, Cognitive Development in Instructional Contexts. Allyn & Bacon, 1996.
[7] D. Cook and L. Holder, “Graph-Based Data Mining,” IEEE Intelligent Systems, vol. 15, no. 2, pp. 32-41, 2000.
[8] DARPA, Transfer Learning (BAA 05-29), 2006.
[9] Transfer on Trial, D. Detterman and R. Sternberg, eds. Ablex Publishing, 1993.
[10] C. Fidoplastis, C. Stapleton, J. Whiteside, C. Hughes, S. Flore, G. Martin, J. Rolland, and E. Smith, “Human Experience Modeler: Context-Driven Cognitive Retraining to Facilitate Transfer of Learning,” CyberPsychology and Behavior, vol. 9, no. 2, pp. 183-187, 2006.
[11] T. Gartner, “Kernel Methods for Mining Graph Data,” Mining Graph Data, D. Cook and L. Holder, eds. John Wiley & Sons, 2006.
[12] M. Gick and K. Holyoak, “Scheme Induction and Analogical Transfer,” Cognitive Psychology, vol. 15, pp. 1-38, 1983.
[13] N. Gorski and J. Laird, “Experiments in Transfer across Multiple Learning Mechanisms,” Proc. Int'l Conf. Machine Learning (ICML) Workshop Structural Knowledge Transfer for Machine Learning, 2006.
[14] J. Greeno, D. Smith, and J. Moore, “Transfer of Situated Learning,” Transfer on Trial, D. Detterman and R. Sternberg, eds. Ablex Publishing, 1993.
[15] J. Hayes and H. Simon, “Psychological Differences among Problem Isomorphs,” Cognitive Theory, N.J. Castellan, D.B. Pisoni, and G.R. Potts, eds. Erlbaum, 1977.
[16] L. Holder and D. Cook, “Graph-Based Relational Learning: Current and Future Directions,” ACM SIGKDD Explorations, vol. 5, no. 1, pp. 90-93, 2003.
[17] E. Holton III and T. Baldsin, Improving Learning Transfer in Organizations. John Wiley & Sons, 2003.
[18] A. Inokuchi, T. Washio, and H. Motoda, “Complete Mining of Frequent Patterns from Graphs: Mining Graph Data,” Machine Learning, vol. 50, no. 3, pp. 321-354, 2003.
[19] M. Kuramochi and G. Karypis, “Finding Frequent Patterns in a Large Sparse Graph,” Data Mining and Knowledge Discovery, 2005.
[20] N. Love, “Transfer Learning Evaluation with Relational Nets,” Proc. Int'l Conf. Machine Learning (ICML) Workshop Structural Knowledge Transfer for Machine Learning, 2006.
[21] Z. Marx, M. Rosenstein, and L. Kaelbling, “Transfer Learning with an Ensemble of Background Tasks,” Proc. Conf. Neural Information Processing Systems (NIPS) Workshop Inductive Transfer: 10 Years Later, 2005.
[22] A. Niculescu-Mizil and R. Caruana, “Learning the Structure of Related Tasks,” Proc. Conf. Neural Information Processing Systems (NIPS) Workshop Inductive Transfer: 10 Years Later, 2005.
[23] S. Nijssen and J. Kok, “A Quickstart in Frequent Structure Mining Can Make a Difference,” Proc. 10th ACM SIGKDD Int'l Conf. Knowledge Discovery and Data Mining (KDD '04), 2004.
[24] J. Ormrod, Human Learning. Pearson Education, 2004.
[25] D. Perkins and G. Salomon, “Transfer of Learning,” International Encyclopedia of Education. Pergamon Press, 1992.
[26] Quake III Arena, http://www.idsoftware.com/games/quakequake3-arena , 2006.
[27] J. Rissanen, Stochastic Complexity in Statistical Inquiry. World Scientific, 1989.
[28] H. Simon, Why Should Machines Learn? In Machine Learning: An Artificial Intelligence Approach, R. Michalski, J. Carbonell, and T.Mitchell, eds. Tioga Publishing, pp. 25-37, 1983.
[29] M. Singley and J. Anderson, Transfer of Cognitive Skill. Harvard Univ. Press, 1989.
[30] E. Talvitie and S. Singh, “An Experts Algorithm for Transfer Learning,” Proc. 20th Int'l Joint Conf. Artificial Intelligence (IJCAI '07), pp. 1065-1070, 2007.
[31] M. Taylor, S. Whiteson, and P. Stone, “Transfer Learning for Policy Search Methods,” Proc. Int'l Conf. Machine Learning (ICML) Workshop Structural Knowledge Transfer for Machine Learning, 2006.
[32] M. Taylor and P. Stone, “Behavior Transfer for Value-Function-Based Reinforcement Learning,” Proc. Fourth Int'l Joint Conf. Autonomous Agents and Multi Agent Systems (AAMAS '05), pp. 53-59, 2005.
[33] E. Thorndike, Educational Psychology. Columbia Univ. Press, 1913.
[34] E. Thorndike and R. Woodworth, “The Influence of Improvement in One Mental Function upon the Efficiency of Other Functions (I),” Psychological Rev., vol. 8, pp. 247-261, 1901.
[35] S. Thrun, “Is Learning the N-th Thing Any Easier than Learning the First?” Advances in Neural Processing Systems, vol. 8, pp. 640-646, 1996.
[36] L. Torrey, J. Shavlik, T. Walker, and R. Maclin, “Relational Skill Transfer via Advice Taking,” Proc. Int'l Conf. Machine Learning (ICML) Workshop Structural Knowledge Transfer for Machine Learning, 2006.
[37] X. Yan and J. Han, “gSpan: Graph-Based Substructure Pattern Mining,” Proc. IEEE Int'l Conf. Data Mining (ICDM '02), 2002.
[38] K. Yoshida, H. Motoda, and N. Indurkhya, “Graph-Based Induction as a Unified Learning Framework,” J. Applied Intelligence, vol. 4, pp. 297-328, 1994.
[39] G. Youngblood, B. Nolen, M. Ross, and L. Holder, “Building Test Beds for AI with the Q3 Mod Base,” Proc. Second Int'l Conf. Artificial Intelligence and Interactive Digital Entertainment (AIIDE '06), pp. 153-154, 2006.
[40] G. Youngblood and L. Holder, “Evaluating Human-Consistent Behavior in a Real-Time First-Person Entertainment-Based Artificial Environment,” Proc. 16th Int'l Conf. Florida Artificial Intelligence Research Soc. (FLAIRS '03), pp. 32-36, 2003.

Index Terms:
data mining, graph algorithms, transfer learning, games
Citation:
Diane J. Cook, Lawrence B. Holder, G. Michael Youngblood, "Graph-Based Analysis of Human Transfer Learning Using a Game Testbed," IEEE Transactions on Knowledge and Data Engineering, vol. 19, no. 11, pp. 1465-1478, Nov. 2007, doi:10.1109/TKDE.2007.190634
Usage of this product signifies your acceptance of the Terms of Use.