Time traveler, 70% man 30% fish (fishy bastard) and Electronics Engineering student.
See more
…by 5 numbers w1, w2, w3, w4, b such that the policy decision…by 5 numbers w1, w2, w3, w4, b such that the policy decision to select next action is made according to:
r
n
w1, w2, w3, w4, b
