while not grid.game_over():
a = policy[s]
a = random_action(a)
r = grid.move(a)
s = grid.current_state()
states_and_rewards.append((s, r))
return states_and_rewards
if __name__ == '__main__':
grid = standard_grid()
print("Rewards: ")
print_values(grid.rewards, grid)
states = grid.all_states()
#initialize Policy
policy = {
(2, 0): 'U',
(1, 0): 'U',
(0, 0): 'R',
(0, 1): 'R',
(0, 2): 'R',
(1, 2): 'R',
(2, 1): 'R',
(2, 2): 'R',
(2, 3): 'U',
}
def max_dict(d):
max_key = None
max_value = float('-inf')
for k, v in d.items():
if v > max_value:
max_value = v
max_key = k
return max_key, max_value
if __name__ == '__main__':
grid = negative_grid(step_cost=-0.1)
print('Rewards: ')
print_values(grid.rewards, grid)
states = grid.all_states()
#initialize Q
Q = {}
for s in states:
Q[s] = {}
for a in ALL_POSSIBLE_ACTIONS:
Q[s][a] = 0
#initialize Count
update_counts = {}
update_counts_sa = {}
for s in states:
update_counts_sa[s] = {}