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)
Is There a Preference in the Linear Programming Framework?
In our case, we want to and a solution, any solution is ok. We don't need to find a specific solutiond so there will be, for example, potentially multiple reward functions that are all consistent with some optimal policy. And that's perfectly finey, so long as all of them end at insuring that the preferences are satisfied. So i think in applications, one would have to have an introuction loop where alice observes, gives new reward functions, bob continues to optimize over time. This is discontinues for a while in order to really get to the rooto, what the task is.
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