|
JAIST Repository >
d. 融合科学系 >
d10. 学術雑誌論文等 >
d10-1. 雑誌掲載論文 >
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/10119/18238
|
| タイトル: | Analyses of Tabular AlphaZero on Strongly-Solved Stochastic Games |
| 著者: | HSUEH, CHU-HSUAN
IKEDA, KOKOLO
WU, I-CHEN
CHEN, JR-CHANG
HSU, TSAN-SHENG |
| キーワード: | AlphaZero
board games
Chinese dark chess
EinStein würfelt nicht!
reinforcement learning
stochastic games
tabular |
| 発行日: | 2023-02-21 |
| 出版者: | Institute of Electrical and Electronics Engineers (IEEE) |
| 誌名: | IEEE Access |
| 巻: | 11 |
| 開始ページ: | 18157 |
| 終了ページ: | 18182 |
| DOI: | 10.1109/ACCESS.2023.3246638 |
| 抄録: | The AlphaZero algorithm achieved superhuman levels of play in chess, shogi, and Go by learning without domain-specific knowledge except for game rules. This paper targets stochastic games and investigates whether AlphaZero can learn theoretical values and optimal play. Since the theoretical values of stochastic games are expected win rates, not a simple win, loss, or draw, it is worth investigating the ability of AlphaZero to approximate expected win rates of positions. This paper also thoroughly studies how AlphaZero is influenced by hyper-parameters and some implementation details. The analyses are mainly based on AlphaZero learning with lookup tables. Deep neural networks (DNNs) like the ones in the original AlphaZero are also experimented and compared. The tested stochastic games include reduced and stronglysolved variants of Chinese dark chess and EinStein würfelt nicht!. The experiments showed that AlphaZero could learn policies that play almost optimally against the optimal player and could learn values accurately. In more detail, such good results were achieved by different hyper-parameter settings in a wide range, though it was observed that games on larger scales tended to have a little narrower range of proper hyper-parameters. In addition, the results of learning with DNNs were similar to lookup tables. |
| Rights: | CHU-HSUAN HSUEH, KOKOLO IKEDA, I-CHEN WU, JR-CHANG CHEN, and TSAN-SHENG HSU, IEEE Access, 11, 2023, 18157-18182. DOI: 10.1109/ACCESS.2023.3246638. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. For more information, see https://creativecommons.org/licenses/by-nc-nd/4.0/ |
| URI: | http://hdl.handle.net/10119/18238 |
| 資料タイプ: | publisher |
| 出現コレクション: | d10-1. 雑誌掲載論文 (Journal Articles)
|
このアイテムのファイル:
| ファイル |
記述 |
サイズ | 形式 |
|---|
| I-IKEDA-K0405-13.pdf | | 3874Kb | 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。
|
