AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
The Benefit of Bottlenecks in Evolving Artificial Intelligence with David Ha - #535
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Is There a Sample Efficiency?
It actually takes a bit more time to train or to evolve the policy for to be able to perform the taskb. The way i think about these issues is that there is a few dimensions you can work on optimising the sample cy like maybe reducing an r l algrithm from 200 million time steps to 100 million time steps t achieve some score. Or you can think at o sample efficiency in terms of zero shot transfer. So one can argue that oki spent all this time figuring out the policy on using hard attention in this paper, but if you give anew environment, which is not the same as the original environment, but one that has has some augmentation to it, we
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