ダウンロード数: 33
このアイテムのファイル:
| ファイル | 記述 | サイズ | フォーマット | |
|---|---|---|---|---|
| 2130-15.pdf | 5.28 MB | Adobe PDF | 見る/開く |
| タイトル: | Distribution of solutions of FreeCell (Algebraic System, Logic, Language and Related Areas in Computer Science) |
| 著者: | JIMBO, Shuji Yamada, Kotaro Imamura, Sho Ueno, Kazuki Okada, Hiromu |
| 著者名の別形: | 神保, 秀司 山田, 晃太郎 今村, 奨 上野, 一樹 岡田, 拡 |
| キーワード: | deep learning A* algorithm search algorithm FreeCell |
| 発行日: | Oct-2019 |
| 出版者: | 京都大学数理解析研究所 |
| 誌名: | 数理解析研究所講究録 |
| 巻: | 2130 |
| 開始ページ: | 85 |
| 終了ページ: | 90 |
| 抄録: | There is a plan by the authors for developing a FreeCell solver by supervised deep learning that searches very few positions as compared with solvers currently released. A large number of solutions of high quality to initial positions in FreeCell are required for the supervised deep learning. A FreeCell solver without deep learning is being developed to make the data sets for deep learning. In this paper, construction of the latter FreeCell solver and the distribution of solutions to initial positions of FreeCell obtained by experiments using the solver are described. |
| URI: | http://hdl.handle.net/2433/254751 |
| 出現コレクション: | 2130 代数系、論理、言語と計算機科学の周辺 |
このリポジトリ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。