Deep learning and computer chess: Giraffe
This study aims to bridge the gap between advanced machine learning techniques and strategic game theory, embracing the transformative impact of Artificial Intelligence in the world of chess. It focuses on building a deep-learning chess engine, Giraffe, which is the first-ever neural network model t...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/175086 |
| _version_ | 1826118114042970112 |
|---|---|
| author | Chan, Eu Ching |
| author2 | He Ying |
| author_facet | He Ying Chan, Eu Ching |
| author_sort | Chan, Eu Ching |
| collection | NTU |
| description | This study aims to bridge the gap between advanced machine learning techniques and strategic game theory, embracing the transformative impact of Artificial Intelligence in the world of chess. It focuses on building a deep-learning chess engine, Giraffe, which is the first-ever neural network model to evaluate positions by exploring the application of neural network techniques in evaluating chess positions, digging into the network architecture, and training methodologies using extensive game datasets. The trained evaluation network then acts as an early playout termination in Monte-Carlo Tree Search (MCTS).
The report highlights the engine’s ability to discover all its domain-specific knowledge, with minimal information given by the dataset. By conducting a 100-game match with each engine, this report will demonstrate the effectiveness of Giraffe through comparative analysis with traditional evaluation algorithms. |
| first_indexed | 2024-10-01T04:38:06Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/175086 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:38:06Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1750862024-04-19T15:42:13Z Deep learning and computer chess: Giraffe Chan, Eu Ching He Ying School of Computer Science and Engineering YHe@ntu.edu.sg Computer and Information Science This study aims to bridge the gap between advanced machine learning techniques and strategic game theory, embracing the transformative impact of Artificial Intelligence in the world of chess. It focuses on building a deep-learning chess engine, Giraffe, which is the first-ever neural network model to evaluate positions by exploring the application of neural network techniques in evaluating chess positions, digging into the network architecture, and training methodologies using extensive game datasets. The trained evaluation network then acts as an early playout termination in Monte-Carlo Tree Search (MCTS). The report highlights the engine’s ability to discover all its domain-specific knowledge, with minimal information given by the dataset. By conducting a 100-game match with each engine, this report will demonstrate the effectiveness of Giraffe through comparative analysis with traditional evaluation algorithms. Bachelor's degree 2024-04-19T04:58:18Z 2024-04-19T04:58:18Z 2024 Final Year Project (FYP) Chan, E. C. (2024). Deep learning and computer chess: Giraffe. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175086 https://hdl.handle.net/10356/175086 en SCSE23-0344 application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Chan, Eu Ching Deep learning and computer chess: Giraffe |
| title | Deep learning and computer chess: Giraffe |
| title_full | Deep learning and computer chess: Giraffe |
| title_fullStr | Deep learning and computer chess: Giraffe |
| title_full_unstemmed | Deep learning and computer chess: Giraffe |
| title_short | Deep learning and computer chess: Giraffe |
| title_sort | deep learning and computer chess giraffe |
| topic | Computer and Information Science |
| url | https://hdl.handle.net/10356/175086 |
| work_keys_str_mv | AT chaneuching deeplearningandcomputerchessgiraffe |