Adaptive critic design in learning to play game of Go

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 1, Issue , 1997, Pages 1-4

  Zaman, Raonak ^a   Prokhorov, Danil ^a   Wunsch, Donald C ^a  

^a TEXAS TECH UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE CRITIC DESIGNS; BRANCHING FACTORS; KNOWLEDGE BASED; LEARNING TO PLAY; PUBLIC DOMAIN PROGRAMS; RELATIVE STRENGTH; SEARCH TECHNIQUE; UTILITY FUNCTIONS;

KNOWLEDGE BASED SYSTEMS; NEURAL NETWORKS; PATTERN MATCHING; SOFTWARE TESTING; GAME THEORY; LEARNING SYSTEMS;

COMPLEX NETWORKS; NEURAL NETWORKS;

ADAPTIVE CRITIC DESIGN; SOFTWARE PACKAGE WALLY;

EID: 0030650665     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.611623     Document Type: Conference Paper

References (9)

1. Bill Newman, "Wally-a Simple Minded Go-program," Shareware Go program available by anonymous ftp from ftp://imageek. york. cuny. edu/nngs/Go/comp/.
2. "The game of Go," by Arthur Smith, Charles Tuttle Co., Tokyo, Japan, 1956.
3. S. Sutton, " Learning to predict by the method of temporal differences," Machine learning, No. 3, 1988, pp. 9-44.
4. G. Tesauro, "Practical Issues in temporal difference learning," Machine learning, No. 8, 1992, pp. 257-278.
5. N. N. Schraudolph, P. Dyan, T. J. Sejnowski, "Temporal learning of position evaluation in the game of Go," Advances in Neural Information Processing, Vol. 6, 1994, pp. 817-824.
6. H. W. Chan, I. King, J. C. Lui, "Performance analysis of a new updating rule for TD(X) learning in feedforward networks for position evaluation in Go game," in Proceedings of the ICNN, Vol. 3, Washington DC, 1996, pp. 1716-1720.
7. D. Prokhorov, D. C. Wunsch H, "Adaptive critic designs," accepted in IEEE Trans. On Neural Networks.
8. D. Prokhorov, R. Santiago, D. C. Wunsch II, "Adaptive critic designs: a case study for neurocontrol," Neural Networks, vol. 8, no. 9, 1995, pp. 1367-1372.
9. P. Werbos and X. Pang, "Generalized Maze Navigation: SRN Critics Solve What Feedforward or Hebbian Nets Cannot", in the Proceedings of the Ninth Yale Workshop on Adaptive and Learning Systems, New Haven CT, 1996, pp. 51-58.