def simple_example():
grid = Gridworld.default_grid()
print('Rewards:')
print_values(grid.rewards, grid)
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',
}
values = first_visit_monte_carlo(grid, 100, policy)
print('Values:')
print_values(values, grid)
print('Policy:')
print_policy(policy, grid)
def simple_example():
grid = Gridworld.default_grid()
print('Rewards:')
print_values(grid.rewards, grid)
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',
}
values = td_zero(grid, policy)
print('Values:')
print_values(values, grid)
print('Policy:')
print_policy(policy, grid)
def mc_prediction():
grid = Gridworld.default_grid()
print('Rewards:')
print_values(grid.rewards, grid)
policy = {
(2, 0): 'U',
(1, 0): 'U',
(0, 0): 'R',
(0, 1): 'R',
(0, 2): 'R',
(1, 2): 'U',
(2, 1): 'L',
(2, 2): 'U',
(2, 3): 'L',
}
values, deltas = approx_monte_carlo(grid, policy)
plt.plot(deltas)
plt.show()
print('Values:')
print_values(values, grid)
print('Policy:')
print_policy(policy, grid)
def simple_example():
grid = Gridworld.default_grid()
values_uniform = policy_evaluation(grid, 1)
print('values for uniformly random actions:')
print_values(values_uniform, grid)
print('\n\n')
fixed_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',
}
print_policy(fixed_policy, grid)
fixed_values = policy_evaluation(grid, 0.9, fixed_policy)
print('Values for fixed policy:')
print_values(fixed_values, grid)