4min chapter

AXRP - the AI X-risk Research Podcast cover image

12 - AI Existential Risk with Paul Christiano

AXRP - the AI X-risk Research Podcast

CHAPTER

Is There a Way to Improve Imitative Reenforcement Learning?

Imitation learning works well for things where you can a evaluate what's going to happen, butfer things to cant. In inverse reinforcement learning we need to look at a human who's saying these things about what they want over the long term and decide which them are errors. The most developed form of this in the situation that we are now seems very hard to get right. I think my basic current ake is like, the game seems pretty rough, or like we don't have a great menu of them available right now. E train a i systems to make predictions about all the like things you can easily measure. And then train an ai system till i predict the outcome of the

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