transition_matrix.py

import numpy as np
T = np.load('datasets/T.npy')
for i in range(12):
    for j in range(4):
        print (T[i,:,j])
        
'''
[0.9 0.1 0.  0.  0.  0.  0.  0.  0.  0.  0.  0. ]  for starting state (1,1) and action Down
[0.9 0.  0.  0.  0.1 0.  0.  0.  0.  0.  0.  0. ]  for starting state (1,1) and action Left 
[0.1 0.1 0.  0.  0.8 0.  0.  0.  0.  0.  0.  0. ]  for starting state (1,1) and action Up
[0.1 0.8 0.  0.  0.1 0.  0.  0.  0.  0.  0.  0. ]  for starting state (1,1) and action Right and so on
[0.1 0.8 0.1 0.  0.  0.  0.  0.  0.  0.  0.  0. ]
[0.8 0.2 0.  0.  0.  0.  0.  0.  0.  0.  0.  0. ]
[0.1 0.8 0.1 0.  0.  0.  0.  0.  0.  0.  0.  0. ]
[0.  0.2 0.8 0.  0.  0.  0.  0.  0.  0.  0.  0. ]
[0.  0.1 0.8 0.1 0.  0.  0.  0.  0.  0.  0.  0. ]
[0.  0.8 0.1 0.  0.  0.  0.1 0.  0.  0.  0.  0. ]
[0.  0.1 0.  0.1 0.  0.  0.8 0.  0.  0.  0.  0. ]
[0.  0.  0.1 0.8 0.  0.  0.1 0.  0.  0.  0.  0. ]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0.8 0.  0.  0.  0.2 0.  0.  0.  0.  0.  0.  0. ]
[0.1 0.  0.  0.  0.8 0.  0.  0.  0.1 0.  0.  0. ]
[0.  0.  0.  0.  0.2 0.  0.  0.  0.8 0.  0.  0. ]
[0.1 0.  0.  0.  0.8 0.  0.  0.  0.1 0.  0.  0. ]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0.  0.  0.8 0.  0.  0.  0.1 0.1 0.  0.  0.  0. ]
[0.  0.  0.1 0.  0.  0.  0.8 0.  0.  0.  0.1 0. ]
[0.  0.  0.  0.  0.  0.  0.1 0.1 0.  0.  0.8 0. ]
[0.  0.  0.1 0.  0.  0.  0.  0.8 0.  0.  0.1 0. ]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
[0.  0.  0.  0.  0.8 0.  0.  0.  0.1 0.1 0.  0. ]
[0.  0.  0.  0.  0.1 0.  0.  0.  0.9 0.  0.  0. ]
[0.  0.  0.  0.  0.  0.  0.  0.  0.9 0.1 0.  0. ]
[0.  0.  0.  0.  0.1 0.  0.  0.  0.1 0.8 0.  0. ]
[0.  0.  0.  0.  0.  0.  0.  0.  0.1 0.8 0.1 0. ]
[0.  0.  0.  0.  0.  0.  0.  0.  0.8 0.2 0.  0. ]
[0.  0.  0.  0.  0.  0.  0.  0.  0.1 0.8 0.1 0. ]
[0.  0.  0.  0.  0.  0.  0.  0.  0.  0.2 0.8 0. ]
[0.  0.  0.  0.  0.  0.  0.8 0.  0.  0.1 0.  0.1]
[0.  0.  0.  0.  0.  0.  0.1 0.  0.  0.8 0.1 0. ]
[0.  0.  0.  0.  0.  0.  0.  0.  0.  0.1 0.8 0.1]
[0.  0.  0.  0.  0.  0.  0.1 0.  0.  0.  0.1 0.8]
[0.  0.  0.  0.  0.  0.  0.  0.8 0.  0.  0.1 0.1]
[0.  0.  0.  0.  0.  0.  0.  0.1 0.  0.  0.8 0.1]
[0.  0.  0.  0.  0.  0.  0.  0.  0.  0.  0.1 0.9]
[0.  0.  0.  0.  0.  0.  0.  0.1 0.  0.  0.  0.9]
'''