Rohin Shah
TalkRL: The Reinforcement Learning Podcast
Using Humans in the Training Loop, Is That Really the Case?
Interview with doctor natasha jakes, senior research scientist at google. Natasha asks why interacting with humans is so much harder than acting with simulated orel agents. "You can't just put the human into the training loop in the way you can put a simulated arrel agent," she says. Humans are significantly more diverse than simulated our allegence and don't all act the same way.
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.
