Deep learning and computer chess (part 2)
The dominant approach to computer chess has typically been through the use of Minimax-based chess engines. In recent years, Monte Carlo Tree Search (MCTS) game engines have seen success, with the advent of AlphaZero and Leela Chess Zero. However, there is still much to explore regarding the us...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/166646 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-166646 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1666462023-05-12T15:36:39Z Deep learning and computer chess (part 2) Lee, Zachary Varella Zheyu, He Ying School of Computer Science and Engineering YHe@ntu.edu.sg Engineering::Computer science and engineering The dominant approach to computer chess has typically been through the use of Minimax-based chess engines. In recent years, Monte Carlo Tree Search (MCTS) game engines have seen success, with the advent of AlphaZero and Leela Chess Zero. However, there is still much to explore regarding the use of MCTS in the domain of chess. This paper evaluates the efficacy of an MCTS-based engine in the area of chess. On top of the base MCTS engine, several enhancements were proposed and implemented, including early playout termination, progressive bias, progressive unpruning, decisive moves, epsilon-greedy search, score bounded Monte-Carlo tree search, and root parallelization. Each enhancement was implemented in stages, and the performance of the enhancement was measured by comparing it to the model from the previous stage. It was determined that early playout termination, progressive unpruning, score bounded search, and root parallelization were effective in improving the playing strength of the engine. However, decisive moves and epsilon-greedy search negatively impacted the engine’s performance. From the results, it appears that it is possible to adapt an MCTS model to the realm of chess through the aid of several enhancements such that can compete with the traditional Minimax approach, with much room for improvement available. Bachelor of Engineering (Computer Science) 2023-05-08T08:09:46Z 2023-05-08T08:09:46Z 2023 Final Year Project (FYP) Lee, Z. V. Z. (2023). Deep learning and computer chess (part 2). Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166646 https://hdl.handle.net/10356/166646 en SCSE22-0133 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering |
spellingShingle |
Engineering::Computer science and engineering Lee, Zachary Varella Zheyu, Deep learning and computer chess (part 2) |
description |
The dominant approach to computer chess has typically been through the use of
Minimax-based chess engines. In recent years, Monte Carlo Tree Search (MCTS) game
engines have seen success, with the advent of AlphaZero and Leela Chess Zero. However,
there is still much to explore regarding the use of MCTS in the domain of chess.
This paper evaluates the efficacy of an MCTS-based engine in the area of chess. On
top of the base MCTS engine, several enhancements were proposed and implemented,
including early playout termination, progressive bias, progressive unpruning, decisive moves,
epsilon-greedy search, score bounded Monte-Carlo tree search, and root parallelization. Each
enhancement was implemented in stages, and the performance of the enhancement was
measured by comparing it to the model from the previous stage.
It was determined that early playout termination, progressive unpruning, score
bounded search, and root parallelization were effective in improving the playing strength of
the engine. However, decisive moves and epsilon-greedy search negatively impacted the
engine’s performance.
From the results, it appears that it is possible to adapt an MCTS model to the realm of
chess through the aid of several enhancements such that can compete with the traditional
Minimax approach, with much room for improvement available. |
author2 |
He Ying |
author_facet |
He Ying Lee, Zachary Varella Zheyu, |
format |
Final Year Project |
author |
Lee, Zachary Varella Zheyu, |
author_sort |
Lee, Zachary Varella Zheyu, |
title |
Deep learning and computer chess (part 2) |
title_short |
Deep learning and computer chess (part 2) |
title_full |
Deep learning and computer chess (part 2) |
title_fullStr |
Deep learning and computer chess (part 2) |
title_full_unstemmed |
Deep learning and computer chess (part 2) |
title_sort |
deep learning and computer chess (part 2) |
publisher |
Nanyang Technological University |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/166646 |
_version_ |
1770567299237937152 |