人工智能2016 · 分享于 Hacker News
Deepmind Navigates 3D Maze WithAsynchronous Methods 4 Deep Reinforcement Learning
探索《Deepmind Navigates 3D Maze WithAsynchronous Methods 4 Deep Reinforcement Learning》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Yatupem ·
AlphaGo beats the world champion Lee Sedol in first of five matches
1,085 赞同573 评论
Ysama ·
OpenAI Universe
1,021 赞同129 评论
Yrezist808 ·
BlazingDB uses GPUs to manipulate huge databases in no time
121 赞同69 评论
Ynopakos ·
Visual Doom AI Competition
118 赞同25 评论
Ymelqdusy ·
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
118 赞同25 评论
Yborisjabes ·
Is AlphaZero really a breakthrough in AI?
114 赞同81 评论
Yfchollet ·
Deep Reinforcement Learning Using Keras and OpenAI Gym
94 赞同2 评论
Yrubenfiszel ·
Reinforcement Learning and DQN – learning to play from pixels
60 赞同9 评论
Ynefitty ·
How Far to AI Utopia?
51 赞同36 评论
Yvonnik ·
Deepmind Navigates 3D Maze WithAsynchronous Methods 4 Deep Reinforcement Learning
11 赞同0 评论
Yfitzwatermellow ·
Asynchronous Methods for Deep Reinforcement Learning
5 赞同0 评论
YRadim ·
Google DeepMind: Asynchronous Methods for Deep Reinforcement Learning
3 赞同0 评论
Ywickedgain ·
Google DeepMind AI finds its way through a 3D maze by 'sight'
2 赞同1 评论
Ybronz ·
Asynchronous Methods for Deep Reinforcement Learning
2 赞同0 评论