如何在電子遊戲中變得更好, 根據寶寶 – 布賴恩·克里斯蒂安

探索人工智能係統 Deep Q Networks 發生了什麼 (DQN) 試圖擊敗雅達利遊戲蒙特祖瑪的複仇.

—

在 2013, a group of researchers wanted to create an AI system that could beat every Atari game. They developed a system called Deep Q Networks (DQN) and less than two years later, it was superhuman. But there was one notable exception. When playing Montezuma’s Revenge, DQN couldn’t score a single point. What was it that made this game so vexingly difficult for AI? Brian Christian investigates.

Lesson by Brian Christian, directed by Gavin Edwards, Movult.

支持我們的非營利使命
———————————————-
在 Patreon 上支持我們: http://bit.ly/TEDEDPatreon
查看我們的商品: http://bit.ly/TEDEDShop
———————————————-

聯繫我們
———————————————-
註冊我們的通訊: http://bit.ly/TEDEDNewsletter
訂閱wocomoMUSIC: http://bit.ly/TEDEDFacebook
在推特上找到我們: http://bit.ly/TEDEDTwitter
在 Instagram 上窺視我們: http://bit.ly/TEDEDInstagram
———————————————-

保持學習
———————————————-
查看完整課程: https://ed.ted.com/lessons/how-to-get-better-at-video-games-according-to-babies-brian-christian
使用其他資源深入挖掘: https://ed.ted.com/lessons/how-to-get-better-at-video-games-according-to-babies-brian-christian#digdeeper

Check out our full book recommendation: https://shop.ed.ted.com/collections/ted-ed-book-recommendations/products/copy-of-1991

動畫師的網站: https://www.movult.com
———————————————-

非常感謝我們的顧客對我們的支持! 沒有你，這個視頻是不可能的! JY Kang, Abhishek Goel, Heidi Stolt, Christina Salvatore, Karlee Finch, Michael Goldberg, Denise A Pitts, Doug Henry, Keven Webb, Mihai Sandu, Deepak Iyer, Javid Gozalov, 美麗的雅浦島, Rebecca Reineke, William Biersdorf, Patricia Alves Panagides, Yvette Mocete, Cyrus Garay, Samuel Barbas, Brighteagle, LadyGeek, Curtis Light, Dianne Palomar, Marin Kovachev, 法赫德·納賽爾·喬杜里, Penelope Misquitta, Hans Peng, Gaurav Mathur, Erik Biemans, 東尼, 米歇爾, 凱蒂和喬許·佩德雷蒂, 桑尼·帕特爾, 陳懷南, 斯蒂娜·博伯格, 金家均, 麥可·布勞恩-博戈斯, zjweele13, Jurjen Geleijn, 安娜-皮奇納昆茨, 埃德拉·帕尼格爾, 托馬斯·蒙加萬, 傑倫·布萊克本, 文卡特·文卡塔克里希南, ReuniteKorea, 亞倫漢森, 羅漢古普塔, 圖通庫女士, 米哈伊爾·施基列夫, 布萊恩理查茲, Cindy O. and Jørgen Østerpart.