def max_dict(d):
max_key = None
max_val = float('-inf')
for k, v in d.items():
if v > max_val:
max_val = v
max_key = k
return max_key, max_val
if __name__ == '__main__':
grid = negative_grid(step_cost=-0.15)
#grid = standard_grid()
print("rewards:")
print_values(grid.rewards, grid)
policy = {}
for s in grid.actions.keys():
policy[s] = np.random.choice(ALL_POSSIBLE_ACTIONS)
Q = {}
returns = {}
states = grid.all_states()
for s in states:
if s in grid.actions:
Q[s] = {}
for a in ALL_POSSIBLE_ACTIONS:
Q[s][a] = 0
returns[(s, a)] = []
import numpy as np
from grid_world import standard_grid, negative_grid
from iterative_policy_eval_det import print_policy, print_values
from monte_carlo_exploring_starts 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(-0.1)
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
t = 1.0