AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Reinforcement Learning for Industrial AI with Pieter Abbeel - #476
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Is the Unsupervised Loss a Part of the Corp Reinforcement Learning Process?
There's a whole airya research around multi task learning that seems to suggest, although you know, they 're certainly arguments against this, that networks generalize better when they have more to do. I'm wondering if part of what you're seeing is the effect of just giving the network something else to learn, as opposed to the unsupervised task contributing to account of the cor reinforcement learning thing that it's supposed to learn. So let me say a bit more about that. i think when we use the contrastive loss on a given image compared to an image at a different time, we're not tying it very directly to the locomotion task versus crawling versus maybe sit or push an
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