Short and long term memory in coevolution

Games provide the perfect test bed for measuring the e ffectiveness of computer generated strategies in a competitive and fun envi ronment. Over the years many di fferent games have been tackled by researchers of computational intelligence with the purpose of creating a intelligent computer player that can challenge human players. In this pa per the authors summarize the research performed over the past two yea rs based on the game of Tempo, where the coevolved strategies were rep r sented by logic rule bases with an adaptive memory. The experiments were set up to investigate the e ffectiveness of various memory structures in a coevolutionary game system, as well as the e ff ctiveness of various recall processes.

[1]  Sushil J. Louis,et al.  Combining Case-Based Memory with Genetic Algorithm Search for Competent Game AI , 2005, ICCBR Workshops.

[2]  L. V. Valen,et al.  A new evolutionary law , 1973 .

[3]  Richard C. Atkinson,et al.  Human Memory: A Proposed System and its Control Processes , 1968, Psychology of Learning and Motivation.

[4]  Zbigniew Michalewicz,et al.  Coevolutionary optimization of fuzzy logic intelligence for strategic decision support , 2005, IEEE Transactions on Evolutionary Computation.

[5]  Zbigniew Michalewicz,et al.  A Historical Population in a Coevolutionary System , 2007, 2007 IEEE Symposium on Computational Intelligence and Games.

[6]  Jordan B. Pollack,et al.  A Population-Differential Method of Monitoring Success and Failure in Coevolution , 2004, GECCO.

[7]  Jordan B. Pollack,et al.  A Game-Theoretic Memory Mechanism for Coevolution , 2003, GECCO.

[8]  Zbigniew Michalewicz,et al.  Coevolutionary TEMPO game , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[9]  Craig W. Reynolds.  Competition, Coevolution and the Game of Tag , 1994 .

[10]  David B. Fogel,et al.  Evolving an expert checkers playing program without using human expertise , 2001, IEEE Trans. Evol. Comput..

[11]  F. Craik,et al.  Levels of Pro-cessing: A Framework for Memory Research , 1975 .

[12]  Hayao Miyagi,et al.  Competitive Co-evolution Model on the Acquisition of Game Strategy , 1996, SEAL.

[13]  Jürgen Branke,et al.  Memory enhanced evolutionary algorithms for changing optimization problems , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[14]  F. Craik,et al.  On the Transfer of Information from Temporary to Permanent Memory [and Discussion] , 1983 .

[15]  Paul J. Darwen,et al.  Why co-evolution beats temporal difference learning at Backgammon for a linear architecture, but not a non-linear architecture , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[16]  Richard K. Belew,et al.  New Methods for Competitive Coevolution , 1997, Evolutionary Computation.

[17]  HighWire Press.  Philosophical Transactions of the Royal Society of London , 1781, The London Medical Journal.

[18]  David B. Fogel,et al.  Blondie24: Playing at the Edge of AI , 2001 .

[19]  Siang Yew Chong,et al.  Evolved neural networks learning Othello strategies , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[20]  Daryl Essam.  Book Review: Blondie24: Playing at the Edge of AI , 2004, Genetic Programming and Evolvable Machines.

[21]  Pattie Maes,et al.  Dynamics of Co-evolutionary Learning , 1996 .

[22]  Zbigniew Michalewicz,et al.  Static experts and dynamic enemies in coevolutionary games , 2007, 2007 IEEE Congress on Evolutionary Computation.

[23]  Dave Cliff,et al.  Tracking the Red Queen: Measurements of Adaptive Progress in Co-Evolutionary Simulations , 1995, ECAL.

[24]  Richard K. Belew,et al.  Methods for Competitive Co-Evolution: Finding Opponents Worth Beating , 1995, ICGA.

[25]  A. Baddeley.  The psychology of memory , 1976 .