Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- def print_value_function(v):
- for i in range(4):
- for j in range(4):
- print("%.3f" % v[i*4 + j], end=' ')
- print()
- def print_policy(policy):
- characters = ['←', '↓', '→', '↑']
- for i in range(4):
- for j in range(4):
- print(characters[np.argmax(policy[i*4 + j])], end=' ')
- print()
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement