hoangminhle / hierarchical_IL_RL

Code for hierarchical imitation learning and reinforcement learning
282 stars 73 forks source link

Expert feedback #2

Open mongoose54 opened 5 years ago

mongoose54 commented 5 years ago

First of all, great work @hoangminhle !

I am going through you code to understand. Overall it is pretty straightforward. I have a quick question: I don't see anywhere in the code how the expert is interacting with the system. Reading the paper I was expecting after INSPECT fails that the system would kick off the expert's annotation subsystem and have them manually label. Am I missing something?

-Alex