Danijar Hafner 2
TalkRL: The Reinforcement Learning Podcast
00:00
The Importance of Hierarchies in Abstract Planning
Do you see future directors having more levels of management to span to higher levels of temporal obstruction? So that's a very good question. I think there are two perspectives on this. One is, yes, you just want a deep hierarchy but maybe these hierarchies can actually be a bit more implicit than that. Maybe we don't want like a fixed number of 10 levels. And what if we can train dynamics models such that some of the features just change less often than others? It seems like a pretty compelling idea. But it's a big open question how to actually learn that and use that for abstract planning.
Transcript
Play full episode
