Episode 22: Archit Sharma, Stanford, on unsupervised and autonomous reinforcement learning
Generally Intelligent
Learning the Doubt Regarding Humans
The first step for me was to actually understand where the problem is. There's nothing like that asks you to do episodic research. A lot of reinforcement learning formalism uses these infinite horizon settings. So it principally like all the algorithms should work without like, but when you actually use them, they're complete garbage.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
