Self-teaching adaptive dynamic programming for Gomoku

Neurocomputing

Volumn 78, Issue 1, 2012, Pages 23-29

  Zhao, Dongbin ^a   Zhang, Zhen ^a   Dai, Yujie ^a  

^a INSTITUTE OF AUTOMATION   (China)

Author keywords

Adaptive dynamic programming; Gomoku; Neural network; Reinforcement learning; Temporal difference learning

Indexed keywords

ADAPTIVE DYNAMIC PROGRAMMING; COMPARISON RESULT; CRITIC NETWORK; GOMOKU; TEMPORAL DIFFERENCE LEARNING;

NEURAL NETWORKS; REINFORCEMENT LEARNING;

DYNAMIC PROGRAMMING;

ADAPTIVE DYNAMIC PROGRAMMING; ALGORITHM; ARCHITECTURE; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPARATIVE STUDY; CONTROLLED STUDY; ERROR; GAME; GOMOKU; LEARNING; PRIORITY JOURNAL; REINFORCEMENT; REWARD; TEACHING;

EID: 82655181840     PISSN: 09252312     EISSN: 18728286     Source Type: Journal    
DOI: 10.1016/j.neucom.2011.05.032     Document Type: Article

References (22)

1. T.K. William, S. Pham, Experience-based learning experiments using Gomoku, in: Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, Charlottesville, Virginia, USA, vol. 2, October 13-16, 1991, pp. 1405-1410.
2. Schaeffer J. The history heuristic and alpha-beta search enhancements in practice. IEEE Trans. Pattern Anal. Mach. Intell. 1989, 11(11):1203-1212.
3. L.V. Allis, H.J. Herik, M.P.H. Huntjens, Gomoku and Threat-Space Search, 2010, doi:. http://10.1.1.96.5836.
4. Freisleben B. A neural network that learns to play five-in-a-row. Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems 1995, 87-90.
5. Teasauro G. Connectionist learning of expert preferences by comparison training. Advances in Neural Information Processing Systems 1989, vol. 1:99-106. Morgan Kaufman, San Francisco.
6. Ishida F., Sasaki T., Sakaguchi Y., Shimai H. Reinforcement-learning agents with different temperature parameters explain the variety of human action-selection behavior in a Markov decision process task. Neurocomputing 2009, 72:1979-1984.
7. G. Tesauro, Neurogammon: a neural-network backgammon program, in: Proceedings of International Joint Conference Neural Networks, San Diego, California, USA, June 17-21, 1990, pp. 33-40.
8. Tesauro G. Practical issues in temporal difference learning. Mach. Learn. 1992, 8:257-277.
9. Tesauro G. TD-Gammon, A self-teaching backgammon program achieves master-level play. Neural Comput. 1994, 6:215-219.
10. J.M. Mo, Study and Practice on Machine Self-Learning of Game-Playing. Master Thesis, Guangxi Normal University, 2003.
11. Baxter J., Tridgell A., Weaver L. Learning to play chess using temporal differences. Mach. Learn. 2000, 40:243-263.
12. Jacek M. Knowledge-free and learning-based methods in intelligent game playing. Stud. Comput. Intell. 2010, 276:71-89.
13. Zhang X.M., Chen Y.Q., Ansari N., Shi Y.Q. Mini-max initialization for function approximation. Neurocomputing 2004, 57:389-409.
14. Martin H J.A., Lope J., Maravall D. Robust high performance reinforcement learning through weighted k-nearest neighbors. Neurocomputing 2011, 74:1251-1259.
15. Barto A.G., Sutton R.S., Anderson C.W. Neuron like adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. 1983, 13:834-847.
16. Werbos P.J. A Menu of Designs for Reinforcement Learning Over Time. Neural Networks for Control 1990, MIT Press, Cambridge.
17. Bertsekas D.P., Tsitsiklis J.N. Neuro-Dynamic Programming 1996, Athena Scientific, Belmont.
18. Dalton J., Balakrishnan S.N. A neighboring optimal adaptive critic for missile guidance. Math. Comput. Model. 1996, 23(1):175-188.
19. D.B. Zhao, J.Q. Yi, D.R. Liu, Particle swarm optimized adaptive dynamic programming, in: Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, Honolulu, Hawaiian Islands, USA, April 1-5, 2007, pp. 32-37.
20. Wiering M.A. Self-play and using an expert to learn to play backgammon with temporal difference learning. J. Intell. Learn. Syst. Appl. 2010, 2:57-68.
21. Sutton R.S., Barto A.G. Reinforcement Learning: An Introduction 1998, The MIT Press, Cambridge.
22. 2010. http://gomocup.wz.cz/gomoku/download.php.