Title :
A neural network that learns to play five-in-a-row
Author :
Reisleben, Bernd
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Siegen Univ., Germany
Abstract :
A neural network that learns to play the board game of five-in-a-row is presented. The basic idea of the approach is to let an appropriately designed network play a series of games against an opponent and use a reinforcement learning algorithm to train the network to evaluate the non-occupied board positions by rewarding good moves and penalizing bad moves. The performance of the proposed network is demonstrated by presenting experimental results
Keywords :
games of skill; learning (artificial intelligence); neural net architecture; bad move penalties; five-in-a-row board game; good move rewards; network performance; network training; neural network; nonoccupied board position evaluation; opponent; reinforcement learning algorithm; Algorithm design and analysis; Application software; Artificial intelligence; Availability; Computer errors; Humans; Machine learning; Neural networks; Proposals; Signal generators;
Conference_Titel :
Artificial Neural Networks and Expert Systems, 1995. Proceedings., Second New Zealand International Two-Stream Conference on
Conference_Location :
Dunedin
Print_ISBN :
0-8186-7174-2
DOI :
10.1109/ANNES.1995.499446