Aaron Havens

icon indicating a website link https://aaronhavens.github.io/

icon company University of Illiinois Urbana-Champaign icon location Champaign-Urbana icon location Safe decision making and control

Results 2 comments of Aaron Havens

Observation of MovementBandits env

@natsuki14 It is the meta-learning objective of the master policy to choose the best sub-policy to reach the current goal. The correct goal remains a latent condition of the MDP....

Terminal states logic for sub-policies

I agree with you. We probably shouldn't be rolling in the expectation of a different policy into a sub-policy advantage. They are practically different MDP's.