Deep Learning and the Game of Checkers
dc.contributor.author | Popic, Jan | |
dc.contributor.author | Boskovic, Borko | |
dc.contributor.author | Brest, Janez | |
dc.coverage.issue | 2 | cs |
dc.coverage.volume | 27 | cs |
dc.date.accessioned | 2022-01-26T08:21:41Z | |
dc.date.available | 2022-01-26T08:21:41Z | |
dc.date.issued | 2021-12-21 | cs |
dc.description.abstract | 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. | en |
dc.format | text | cs |
dc.format.extent | 1-6 | cs |
dc.format.mimetype | application/pdf | en |
dc.identifier.citation | Mendel. 2021 vol. 27, č. 2, s. 1-6. ISSN 1803-3814 | cs |
dc.identifier.doi | 10.13164/mendel.2021.2.001 | en |
dc.identifier.issn | 2571-3701 | |
dc.identifier.issn | 1803-3814 | |
dc.identifier.uri | http://hdl.handle.net/11012/203381 | |
dc.language.iso | en | cs |
dc.publisher | Institute of Automation and Computer Science, Brno University of Technology | cs |
dc.relation.ispartof | Mendel | cs |
dc.relation.uri | https://mendel-journal.org/index.php/mendel/article/view/163 | cs |
dc.rights | Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license | en |
dc.rights.access | openAccess | en |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0 | en |
dc.subject | Artificial Intelligence | en |
dc.subject | Deep Learning | en |
dc.subject | Convolutional Neural Network | en |
dc.subject | Reinforcement Learning | en |
dc.subject | Checkers | en |
dc.title | Deep Learning and the Game of Checkers | en |
dc.type.driver | article | en |
dc.type.status | Peer-reviewed | en |
dc.type.version | publishedVersion | en |
eprints.affiliatedInstitution.faculty | Fakulta strojního inženýrství | cs |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- 163-Article Text-380-3-10-20220124.pdf
- Size:
- 400.68 KB
- Format:
- Adobe Portable Document Format
- Description: