2min chapter

Data Skeptic cover image

Computable AGI

Data Skeptic

CHAPTER

How to Define a Task in a Reinforcement Learning Model

The idea is that your mind is part of the world and so rather than applying that mind to the world we just have a task which specifies everything you're trying to achieve. It's kind of combining them together this is uh hide the gary and idea or dassy in a little bit although this philosophers will get angry for using that. How do we decide what are appropriate tasks? Well i guess the way i was thinking about a task is is just it's something that's specified by my very existence so the fact that i have a particular body with certain urges i need satisfy it implies a task.

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