Deep Learning and the Game of Checkers

被引：0

作者：

Popič J. ^{[1
]}

Bošković B. ^{[1
]}

Brest J. ^{[1
]}

机构：

[1] Institute of Computer Science, Faculty of Electrical Engineering and Computer Science, University of Maribor, Maribor

来源：

Mendel | 2021年 / 27卷 / 02期

关键词：

Artificial intelligence; Checkers; Convolutional neural network; Deep learning; Reinforcement learning;

D O I：

10.13164/mendel.2021.2.001

中图分类号：

学科分类号：

摘要：

In this paper we present an approach which given only a set of rules is able to learn to play the game of Checkers. We utilize neural networks and reinforced learning combined with Monte Carlo Tree Search and alpha-beta pruning. Any human influence or knowledge is removed by generating needed data, for training neural network, using self-play. After a certain number of finished games, we initialize the training and transfer better neural network version to next iteration. We compare different obtained versions of neural networks and their progress in playing the game of Checkers. Every new version of neural network represented a better player. © 2021, Brno University of Technology. All rights reserved.

引用

页码：1 / 6

页数：5

共 10 条

[1]

Baek M., DiMaio F., Anishchenko I., Dauparas J., Ovchinnikov S., Et al., Accu-rate prediction of protein structures and interac-tions using a three-track neural network, Science, 373, 6557, pp. 871-876, (2021)

[2]

Foster D., Deep reinforcement learn-ing, (2018)

[3]

Ioffe S., Szegedy C., Batch normal-ization: Accelerating deep network training by reducing internal covariate shift, Proceedings of the 32Nd International Conference on Machine Learning, 37, pp. 448-456, (2015)

[4]

Samuel A. L., Some studies in machine learning using the game of checkers, IBM Journal of research and development, 3, 3, pp. 210-229, (1959)

[5]

Schaeffer J., Burch N., Bjornsson Y., Kishimoto A., Muller M., Lake R., Lu P., Sutphen S., Checkers is solved, Science, 317, 5844, pp. 1518-1522, (2007)

[6]

Schmidhuber J., Deep learning in neural net-works: An overview, Neural networks, 61, pp. 85-117, (2015)

[7]

Silver D., Et al., Mastering the game of go with deep neural networks and tree search, Nature, 529, (2016)

[8]

Silver D., Hubert T., Schrittwieser J., Antonoglou I., Lai M., Et al., A general reinforcement learning algorithm that masters chess, shogi, and go through self-play, Science, 362, 6419, pp. 1140-1144, (2018)

[9]

Silver D., Schrittwieser J., Simonyan K., Antonoglou I., Huang A., Et al., Mastering the game of go without human knowledge, Nature, 550, (2017)

[10]

Srinidhi C. L., Ciga O., Martel A. L., Deep neural network models for computational histopathology: A survey, Medical Image Anal-ysis, 67, (2021)

← 1 →