AI, Robot
Google DeepMind: The Podcast
How to Train a Neural Network to Give You Feedback in Real Time
Reinforcement learning with a human standing over it, offering feedback at every stage is monumentally slow. So instead we train a newl network that learn s how i would give feedback as the human. And then the denul network can teach you, because it can just oversee all the things you are doing. The reason why this works very well is because evaluating the objective is an easier task than producing the behavior that achieves it. But of course, where this stuff really comes alive is where you take the ideas, take them out of a computer simulation and allow your imagination to roam into the world of embodied ai.
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.
