Danijar Hafner 2
TalkRL: The Reinforcement Learning Podcast
Dreamer V3: A Future of Efficiency
In dreamer v3 because the algorithm is so robust we observed very predictable scaling behavior of the algorithm. So in a sense the world model lets you just trade off more compute to become more data efficient. And I think even today if we want to be ten times more data efficient we can actually do that by increasing the model size and increasing the gradient steps, while waiting longer for the whole thing to train.
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.
