Danijar Hafner 2
TalkRL: The Reinforcement Learning Podcast
The Benefits of Splitting the Agent Into Manager and Worker
splitting the agent into this manager and worker in this way is helpful for learning. It lets your high-level plan much further into the future, right? Because it's only planning over the sequence of goals that change less frequently than the low-level primitive actions. And I think there's a lot more to be done in director, which is changing the goal every 16 steps. So it's only 16 times further that it can look into the future at the high level.
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.
