3min chapter

Lex Fridman Podcast cover image

Oriol Vinyals: DeepMind AlphaStar, StarCraft, Language, and Sequences

Lex Fridman Podcast

CHAPTER

How to Imitate Well in Deep Learning?

We take humans from three thousand a memr and higher. Amemar is just a metric of human skill. The best in the world are at seven thousand, seven thousand. So we say, these replay youre going to try to imitate to predict the next action. For all the actions that you can to see is a four thousand a memar replay. This one is a six thousand a Memar replay. And what's cool about this is then we can ask it to play like a gold level player by setting a beat. It does less actions per minute, which is the number of cliqus,. or number of actions that you will issue in a whole minute. But if

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode