2min chapter

Lex Fridman Podcast cover image

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

Lex Fridman Podcast

CHAPTER

The Challenges of Machine Learning in Go and Starcraft

In go, there's only 400 actions, but one action is what people would call the god action. So i think the problem there is, in terms of action space size is way harder. For humans, maybe the playing stark ofic seems more intuitive because it looks real aminon like the graphics and everything moves smoothly. Whereas i don't know how to min go is a game that i wouldn't really need to study. But for machines, kind of, maybe it's the reverse, yes,. which shows you the gap, actually, between deep learning or machine learning. And however, the hekor brains work a so you developed a lot of really interesting ideas.

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