AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Hierarchical and Continual RL with Doina Precup - #567
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
The Reward Function Is a Result of Computing an L P
We were trying to define the problem, think about what it means to have a task in mind and separate that from this issue of holdiu then specified as a reward. So he does assume that you have a marcovian process and the side effect of that is that we have states. In the real world, we have features, right? We don't have states, but we have some observations. Those are an imperfect representation of what the state might be. But i think they know this limitation, for example, of not having necessarily an md p having features these, or things that are more left for future work, but could potentially be overcome. It would also be really interesting to
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