GAURAV CHAUDHARY
GAURAV CHAUDHARY
I am trying to create a simulation environment using the instructions given in this repo. ###############______________code_____________############################ import gym import robo_gym from robo_gym.wrappers.exception_handling import ExceptionHandling target_machine_ip = '127.0.0.1' # or other...
why is this code not converge for other discrete action environments such as Acrobot and MountainCar?
Does the script of on-policy JSRL work? The commit message suggests it's not complete yet.