AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Hierarchical and Continual RL with Doina Precup - #567
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Using Hierarchical Arel in Multitask Learning
Multitask learning suggests that it can be more computationally efficient to learn, or produce better results, to learn multiple things at once. Hierarchical arel is similar in spirit, but at the level of action. So lower layers would look at very fine resolution in terms of the actions being taken very quickly and lasting only little bits of time. Higher layers may look at actions that take a very long time to complete. It's not as sort of clean as a siennan in the sense that these time scales can be variable,. And we don't necessarily want to separate them out in very determined layers, right? Yo's looping and it's not as clean at all.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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