AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Reinforcement Learning for Industrial AI with Pieter Abbeel - #476
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
The Conjunction of Unsupervised and Reinforcement Learning
Unsupervised learning is something that has been a goal from a research perspective for a while, but it's really played out in big ways and natural language processing recently. And so to make the analogy, there may be natural language proseing. Instead of just generating examples of positive and negative articles, you would instead first train on predicting the next word in a sentence. But only you want to be more data efficient. You want a nodgist? Do something for a minute and at the end know whether you were right or wrong? No, you want to have feedback that's much denser, much more informative.
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