Mastering the game of Go without human knowledge譯文
1. 摘要 人工智能的長期目標是後天自主學習，並且在一些具有挑戰性的領域中實現超人的算法。最近，AlphaGo成爲第一個在圍棋中擊敗人類世界冠軍的程序。AlphaGo的樹搜索使用深度神經網絡來評估棋局和選定下棋位置。神經網絡是利用對人類專業棋手的移動進行監督學習，同時通過自我博弈進行強化學習來進行訓練的。在這裏，我們引入了一種沒有人類的數據、指導或超越遊戲規則的領域知識的、基於強化學習的算法。Al
相關文章
- 1. Mastering the game of Go without human knowledge (AlphaGo Zero)
- 2. 論文《Masteing the game of Go without human knowledge》解讀
- 3. 【論文翻譯】Mastering the game of Go without human knowledge (無師自通---在不借助人類知識的情況下學會圍棋）
- 4. Mastering the game of Go with deep neural networks and tree search (AlphaGo)
- 5. Mastering the game of Go with deep neural networks and tree search 概括
- 6. 翻譯Deep Learning and the Game of Go（1）緒論部分
- 7. Daily Paper 004: Two Forms of Knowledge Representations in the Human Brain
- 8. Mastering Unity 2D Game Development
- 9. AlphaGo是如何煉成的：解讀論文 "Mastering the game of Go with deep neural networks and tree search"
- 10. 【論文翻譯】Mastering the game of Go with deep neural networks and tree search( 用深度神經網絡和樹搜索實現圍棋遊戲)
- 更多相關文章...
- • Eclipse 編譯項目 - Eclipse 教程
- • XSLT
- • Scala 中文亂碼解決
- • Docker容器實戰(七) - 容器眼光下的文件系統
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Mastering the game of Go without human knowledge (AlphaGo Zero)
- 2. 論文《Masteing the game of Go without human knowledge》解讀
- 3. 【論文翻譯】Mastering the game of Go without human knowledge (無師自通---在不借助人類知識的情況下學會圍棋）
- 4. Mastering the game of Go with deep neural networks and tree search (AlphaGo)
- 5. Mastering the game of Go with deep neural networks and tree search 概括
- 6. 翻譯Deep Learning and the Game of Go（1）緒論部分
- 7. Daily Paper 004: Two Forms of Knowledge Representations in the Human Brain
- 8. Mastering Unity 2D Game Development
- 9. AlphaGo是如何煉成的：解讀論文 "Mastering the game of Go with deep neural networks and tree search"
- 10. 【論文翻譯】Mastering the game of Go with deep neural networks and tree search( 用深度神經網絡和樹搜索實現圍棋遊戲)