|
JAIST Repository >
b. 情報科学研究科・情報科学系 >
b11. 会議発表論文・発表資料等 >
b11-1. 会議発表論文・発表資料 >
このアイテムの引用には次の識別子を使用してください:
http://hdl.handle.net/10119/18241
|
| タイトル: | High-performance Algorithms using Deep Learning in Turn-based Strategy Games |
| 著者: | Kimura, Tomihiro
Ikeda, Kokolo |
| キーワード: | Turn-based Strategy Games
Deep Neural Network
Deep Reinforcement Learning
Policy Network
Value Network
AlphaZero
Residual Network |
| 発行日: | 2020-02 |
| 出版者: | SCITEPRESS – Science and Technology Publications, Lda. |
| 誌名: | Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020) |
| 巻: | 2 |
| 開始ページ: | 555 |
| 終了ページ: | 562 |
| DOI: | 10.5220/0008956105550562 |
| 抄録: | The development of AlphaGo has increased the interest of researchers in applying deep learning and reinforcement learning to games. However, using the AlphaZero algorithm on games with complex data structures and vast search space, such as turn-based strategy games, has some technical challenges. The problem involves performing complex data representations with neural networks, which results in a very long learning time. This study discusses methods that can accelerate the learning of neural networks by solving the problem of the data representation of neural networks using a search tree. The proposed algorithm performs better than existing methods such as the Monte Carlo Tree Search (MCTS). The automatic generation of learning data by self-play does not require a big learning database beforehand. Moreover, the algorithm also shows excellent match results with a win rate of more than 85% against the conventional algorithms in the new map which is not used for learning. |
| Rights: | Copyright (C) 2022 SCITEPRESS - Science and Technology Publications. Tomihiro Kimura, Ikeda Kokolo, Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020), 2, 2022, 555-562. DOI: 10.5220/0008956105550562. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. |
| URI: | http://hdl.handle.net/10119/18241 |
| 資料タイプ: | publisher |
| 出現コレクション: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| I-IKEDA-K0405-17.pdf | | 1594Kb | Adobe PDF | 見る/開く |
|
当システムに保管されているアイテムはすべて著作権により保護されています。
|
