|
JAIST Repository >
d. 融合科学系 >
d11. 会議発表論文 >
d11-1. 会議発表論文 >
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/10119/18242
|
| タイトル: | Graph Convolutional Networks for Turn-Based Strategy Games |
| 著者: | Li, Wanxiang
He, Houkuan
Hsueh, Chu-Hsuan
Ikeda, Kokolo |
| キーワード: | Turn-Based Strategy (TBS) Game
Graph Convolutional Neural Networks
Minimax Tree Search |
| 発行日: | 2022-02 |
| 出版者: | SCITEPRESS – Science and Technology Publications, Lda. |
| 誌名: | Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART 2022) |
| 巻: | 2 |
| 開始ページ: | 552 |
| 終了ページ: | 561 |
| DOI: | 10.5220/0010904200003116 |
| 抄録: | In this paper, we research Turn-Based Strategy (TBS) games that allow players to move multiple pieces in one turn and have multiple initial states. Compared to a game like Chess, which allows only one piece to move per turn and has a single initial state, it is difficult to create a strong computer player for such a group of TBS games. Deep learning methods such as AlphaZero and DQN are often used to create strong computer players. Convolutional neural networks (CNNs) are used to output policies and/or values, and input states are represented as “image”-like data. For TBS games, we consider that the relationships among units are more important than their absolute positions, and we attempt to represent the input states as “graphs”. In addition, we adopt graph convolutional neural networks (GCNs) as the suitable networks when inputs are graphs. In this research, we use a TBS game platform TUBSTAP as our test game and propose to (1) represent TUBSTAP game states as graphs, (2) employ GCNs as value network to predict the game result (win/loss/tie) by supervised learning, (3) compare the prediction accuracy of GCNs and CNNs, and (4) compare the playing strength of GCNs and CNNs when the learned value network is incorporated into a tree search. Experimental results show that the combination of graph input and GCN improves the accuracy of predicting game results and the strength of playing TUBSTAP. |
| Rights: | Copyright (C) 2022 SCITEPRESS - Science and Technology Publications. Wanxiang Li, Houkuan He, Chu-Hsuan Hsueh and Kokolo Ikeda, Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART 2022), 2, 2022, 552-561. DOI: 10.5220/0010904200003116. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. |
| URI: | http://hdl.handle.net/10119/18242 |
| 資料タイプ: | publisher |
| 出現コレクション: | d11-1. 会議発表論文 (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-K0405-18.pdf | | 523Kb | 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。
|
