PickVidsOpenAI Plays Hide and Seek…and Breaks The Game! 🤖
推荐理由
OpenAI's hide and seek is one of my favorites
说明
这是2019年由Two Minute Papers发布的一部讲解，主题归在Machine learning & deep learning。它讲的是multi-agent reinforcement learning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：Two Minute Papers covers OpenAI's multi-agent hide-and-seek experiment, in which agents learned emergent tool use and found ways to break the game's rules. It summarizes the 'Emergent Tool Use from Multi-Agent Interaction' paper.这些读者给出的理由，核心是：HN mentions it as a fun and slightly worrying example of AI systems behaving in unintended ways when optimizing.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2020年到2021年，有2位不同的读者在2个不同月份把它推荐出来，其中明确叫别人去看的有0次。适合用一集把一个概念补上的人。抓住它用的那个图像或类比，比背公式重要。如果已经会了基本定义，就把注意力放在它怎么把multi-agent reinforcement learning变成能跟着复述的例子。
视频信息
- 频道
- Two Minute Papers
- 时长
- 6 分 2 秒
- 发布年份
- 2019
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)