create_q_learning.py

import pandas as pd
import numpy
import random

actions = ['up', 'down', 'left', 'right']
states = ['start', 'mousetrap', 'empty', 'cheese', 'end']
n_actions = len(actions)
n_states = len(states)

q_table = pd.DataFrame(np.zeros([n_states, n_actions]), columns=actions)

print (q_table)

"""
    up  down  left  right
0  0.0   0.0   0.0    0.0
1  0.0   0.0   0.0    0.0
2  0.0   0.0   0.0    0.0
3  0.0   0.0   0.0    0.0
4  0.0   0.0   0.0    0.0
"""