Evolving a neural network location evaluator to play Ms. Pac-Man

IEEE 2005 Symposium on Computational Intelligence and Games, CIG'05

Volumn , Issue , 2005, Pages 203-210

  Lucas, Simon M ^a  

^a UNIVERSITY OF ESSEX   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

FEATURE VECTORS; NETWORK LOCATION;

ALGORITHMS;

NEURAL NETWORKS;

EID: 80053632021     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. H.-G. Beyer. Toward a theory of evolution strategies: The (mu, lambda)-theory. Evolutionary Computation, 2(4):381- 407, 1994.
2. J. S. D. Bonet and C. P. Stauffer. Learning to play Pac-Man using incremental reinforcement learning., 1999. http://www.ai.mit.edu/people/ stauffer/Projects/PacMan/.
3. K. Chellapilla and D. Fogel. Evolving an expert checkers playing program without using human expertise. IEEE Transactions on Evolutionary Computation, 5:422 - 428, (2001). (Pubitemid 32949971)
4. D. Floreano, T. Kato, D. Marocco, and E. Sauser. Coevolution of active vision and feature selection. Biological Cybernetics, 90:218 - 228, 2004. (Pubitemid 40877330)
5. M. Gallagher and A. Ryan. When will a genetic algorithm outperform hill climbing? In Proceedings of IEEE Congress on Evolutionary Computation, pages 2462 - 2469. 2003.
6. J. Koza. Genetic Programming: on the programming of computers by means of natural selection. MIT Press, Cambridge, MA, (1992).
7. J. Laird. Using a computer game to develop advanced AI. Computer, 34:70 - 75, 2001. (Pubitemid 32658163)
8. M. Mitchell, J. Holland, and S. Forrest. When will a genetic algorithm outperform hill climbing? In J. Cowan, G. Tesauro, and J. Alspector, editors, Advances in Neural Information Processing Systems 6, pages 51 - 58. Morgan Kaufman, San Mateo, CA, 1994.
9. J. B. Pollack and A. D. Blair. Co-evolution in the successful learning of backgammon strategy. Machine Learning, 32:225-240, 1998. (Pubitemid 40626406)
10. T. Runarsson and S. Lucas. Co-evolution versus self-play temporal difference learning for acquiring position evaluation in small-board Go. IEEE Transactions on Evolutionary Computation, page Submitted August 2004.
11. J. Schaffer, D. Whitley, and L. Eshelman. Combinations of genetic algorithms and neural networks: a survey of the state of the art. In Proceedings of COGANN-92 - IEEE International Workshop on Combinations of Genetic Algorithms and Neural Networks, pages 1 - 37. IEEE, Baltimore, (1992).
12. G. Tesauro. Temporal difference learning and td-gammon. Communications of the ACM, 38(3):58-68, 1995.
13. H.-G. Beyer. Toward a theory of evolution strategies: The (mu, lambda)-theory. Evolutionary Computation, 2(4):381- 407, 1994.
14. J. S. D. Bonet and C. P. Stauffer. Learning to play Pac-Man using incremental reinforcement learning., 1999. http://www.ai.mit.edu/people/ stauffer/Projects/PacMan/.
15. K. Chellapilla and D. Fogel. Evolving an expert checkers playing program without using human expertise. IEEE Transactions on Evolutionary Computation, 5:422 - 428, (2001). (Pubitemid 32949971)
16. D. Floreano, T. Kato, D. Marocco, and E. Sauser. Coevolution of active vision and feature selection. Biological Cybernetics, 90:218 - 228, 2004. (Pubitemid 40877330)
17. M. Gallagher and A. Ryan. When will a genetic algorithm outperform hill climbing? In Proceedings of IEEE Congress on Evolutionary Computation, pages 2462 - 2469. 2003.
18. J. Koza. Genetic Programming: on the programming of computers by means of natural selection. MIT Press, Cambridge, MA, (1992).
19. J. Laird. Using a computer game to develop advanced AI. Computer, 34:70 - 75, 2001. (Pubitemid 32658163)
20. M. Mitchell, J. Holland, and S. Forrest. When will a genetic algorithm outperform hill climbing? In J. Cowan, G. Tesauro, and J. Alspector, editors, Advances in Neural Information Processing Systems 6, pages 51 - 58. Morgan Kaufman, San Mateo, CA, 1994.
21. J. B. Pollack and A. D. Blair. Co-evolution in the successful learning of backgammon strategy. Machine Learning, 32:225-240, 1998. (Pubitemid 40626406)
22. T. Runarsson and S. Lucas. Co-evolution versus self-play temporal difference learning for acquiring position evaluation in small-board Go. IEEE Transactions on Evolutionary Computation, page Submitted August 2004.
23. J. Schaffer, D. Whitley, and L. Eshelman. Combinations of genetic algorithms and neural networks: a survey of the state of the art. In Proceedings of COGANN-92 - IEEE International Workshop on Combinations of Genetic Algorithms and Neural Networks, pages 1 - 37. IEEE, Baltimore, (1992).
24. G. Tesauro. Temporal difference learning and td-gammon. Communications of the ACM, 38(3):58-68, 1995.