Hierarchical Policy

First saw this from Hierarchical Behavior Cloning.

“HBC consists of a low-level policy that is conditioned on future observations sg ∈ S (termed subgoals) and outputs action sequences to try and achieve them, and a high-level policy that predicts future subgoals from the current observation.”

Some more papers on hierarchical planning:

In the Context of RL

So we have two policies:

  • that predicts
  • that predicts to get to the goal states