Step 2: Implement the Reinforcement Learning Algorithm:

self.qnnet.u3(float(maxstring[j])\*np.pi,0,0,q[dim+j])

maxstring = np.binary\_repr(np.argmax(expected\_values), width = dim)

load\_accounts = True, # if accounts are to be loaded backend\_code = 'ibmq\_qasm\_simulator' # backend code
