Computer program that learns to play classic NES games

推荐理由

Watch the whole thing, it's delightful.

强烈推荐fartcannon · 原文2021年2月

说明

这是2013年由suckerpinch发布的一部演示，主题归在Machine learning & deep learning。它讲的是nes game-playing ai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：Tom7 explains and demos software that learns to play NES games by finding score patterns in memory and then searching for inputs that raise it. It is the video companion to his SIGBOVIK paper.这些读者给出的理由，核心是：Loved on HN as a hilarious, brilliant example of hacker-academic work and cited whenever game-playing AI or fuzzing comes up.讲法不绑某一条新闻，过几年仍然可以当材料看。从2015年到2025年，有9位不同的读者在10个不同月份把它推荐出来，其中明确叫别人去看的有2次。适合先看结果再决定要不要深挖的人。先看它做成了什么。如果已经会了基本定义，就把注意力放在它怎么把nes game-playing ai变成能跟着复述的例子。

视频信息

频道

suckerpinch

时长

16 分 18 秒

发布年份

2013

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)