else:
states_and_returns.append((s, G))
G = r + GAMMA * G
states_and_returns.reverse()
return states_and_returns
if __name__ == '__main__':
# use the standard grid again (0 for every step) so that we can compare
# to iterative policy evaluation
grid = standard_grid()
# print rewards
print("rewards:")
print_values(grid.rewards, grid)
# state -> action
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',
}
V = {}
from grid_world import standard_grid, negative_grid
from policy_evaluation import print_values, print_policy
from monte_carlo_es import max_dict
from td0_prediction import random_action
GAMMA = 0.9
ALPHA = 0.1
ALL_POSSIBLE_ACTIONS = ('U', 'D', 'L', 'R')
if __name__ == '__main__':
grid = negative_grid()
# print rewards
print("rewards:")
print_values(grid.rewards, grid)
Q = {}
states = grid.all_states()
for s in states:
Q[s] = {}
for a in ALL_POSSIBLE_ACTIONS:
Q[s][a] = 0
update_counts = {}
update_counts_sa = {}
for s in states:
update_counts_sa[s] = {}
for a in ALL_POSSIBLE_ACTIONS:
update_counts_sa[s][a] = 1.0