search

bradyz / 2020_CARLA_challenge

"Learning by Cheating" (CoRL 2019) submission for the 2020 CARLA Challenge
181 stars 49 forks source link

Alpha Random Controller Variable #30

Open omerXfaruq opened 3 years ago

omerXfaruq commented 3 years ago

Hello there;

In the image_model.py there is an random variable alpha, seems like mixing two outputs. Can you explain what are these? -is lbl_cam target projected into the cam -is out waypoint output generated by the neural network?

image

omerXfaruq commented 3 years ago

Hello @bradyz; https://github.com/bradyz/carla_project/blob/ac791fcf7e59ad80b6908dadc00eb4f26147c065/src/image_model.py#L132

This where I am talking about, it seems it mixes the output generated by the privileged agent with its own output. However it did not make sense to me, is the sensorimotor agent taking privilege from the privileged agent while training?