Rohin Shah
TalkRL: The Reinforcement Learning Podcast
The Reward Learning Paradime
When you described the robot that would ask all these irrelevant questions, i couldn't help thinking, you now, that's the kind of thing a four year old would do. So how do you relate? Can you relate this assistance paradime back to standard an inverse r what is the relationship between these two paradimes? Yes, so inverse rl assumes that it's an example of the reward learning paradine. And then given the, you know, teller operated robot, demonstrations of how to do the task, the robot is then suppose to infer what the task actually was and then be able to do it itself in the future without any uncertainty.
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.
