PickVidsGoogle's DeepMind AI Just Taught Itself To Walk
推荐理由
If you watch videos of AIs learning to run [1] or playing Mario [2]
说明
这是2017年由Insider Tech发布的一部新闻，主题归在Machine learning & deep learning。它讲的是reinforcement learning locomotion这一支里的具体问题，而不是把整个领域扫一遍。适合按兴趣直接看、不打算先补课的人。内容上可以概括成：A two-minute Insider Tech clip on DeepMind's simulated agents that learned to walk, run, jump and climb without guidance, with the goofy resulting gaits.这些读者给出的理由，核心是：HN uses it as a quick example of reinforcement learning agents acquiring locomotion in simulation, rather than recommending it as a deep resource.它贴着当时的技术，看的时候要记得那是那个年份的判断。从2017年到2022年，有0位不同的读者在0个不同月份把它推荐出来，其中明确叫别人去看的有0次。适合想知道那个时间点大家在争什么的人。结论会过时，争论本身仍然有用。如果已经会了基本定义，就把注意力放在它怎么把reinforcement learning locomotion变成能跟着复述的例子。
视频信息
- 频道
- Insider Tech
- 时长
- 1 分 51 秒
- 发布年份
- 2017
同主题更多
- The spelled-out intro to neural networks and backpropagation: building micrograd
- But what is a neural network? | Deep learning chapter 1
- AlphaGo - The Movie | Full award-winning documentary
- Transformers, the tech behind LLMs | Deep Learning Chapter 5
- USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible?
- Lecture 1 | Machine Learning (Stanford)