I just wanted to briefly talk about your decision transformers work. You know, we try not to retread stuff that people have talked about elsewhere too much on this show. So I will just say for starters, that you covered this in pretty good depth on a podcast called Talk RL, middle of last year. And then I have a couple kind of, you know, update questions like, is there any news in the kind of decision transformer world that you think is worth flagging? Yeah, so decision transformer, basically readings reinforcement learning, that's just a single transformer. Read for the learning is like decades of work done on how to build algorithms that optimize the reward given the previous states

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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