def test_homework(self):
grid = [[0, 0, 0], [0, 0, 0]]
goal = [0, len(grid[0]) - 1]
expected_value = [[60.472, 37.193, 0.], [63.503, 44.770, 37.193]]
expected_policy = [['>', '>', '*'], ['>', '^', '^']]
value, policy = homework._stochastic_value(grid, goal)
self.assertEqual(expected_policy, policy)
self.assertAlmostEqual(expected_value, value, 3)
grid = [[0, 1, 0], [0, 0, 0]]
expected_value = [[94.041, 1000., 0.000], [86.082, 73.143, 44.286]]
expected_policy = [['v', ' ', '*'], ['>', '>', '^']]
value, policy = homework._stochastic_value(grid, goal)
self.assertEqual(expected_policy, policy)
self.assertAlmostEqual(expected_value, value, 3)
def test_homework_larger_grid(self):
grid = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0], [0, 1, 1, 0]]
goal = [0, len(grid[0]) - 1]
expected_value = [[57.903, 40.278, 26.066, 0.000],
[47.055, 36.572, 29.994, 27.270],
[53.172, 42.023, 37.775, 45.092],
[77.586, 1000., 1000., 73.546]]
expected_policy = [['>', 'v', 'v', '*'], ['>', '>', '^', '<'],
['>', '^', '^', '<'], ['^', ' ', ' ', '^']]
value, policy = homework._stochastic_value(grid, goal)
self.assertEqual(expected_policy, policy)
self.assertAlmostEqual(expected_value, value, 3)
def test_homework(self):
grid = [[0, 0, 0],
[0, 0, 0]]
goal = [0, len(grid[0]) - 1]
expected_value = [[60.472, 37.193, 0.],
[63.503, 44.770, 37.193]]
expected_policy = [['>', '>', '*'],
['>', '^', '^']]
value, policy = homework._stochastic_value(grid, goal)
self.assertEqual(expected_policy, policy)
self.assertAlmostEqual(expected_value, value, 3)
grid = [[0, 1, 0],
[0, 0, 0]]
expected_value = [[94.041, 1000., 0.000],
[86.082, 73.143, 44.286]]
expected_policy = [['v', ' ', '*'],
['>', '>', '^']]
value, policy = homework._stochastic_value(grid, goal)
self.assertEqual(expected_policy, policy)
self.assertAlmostEqual(expected_value, value, 3)
def test_homework_larger_grid(self):
grid = [[0, 0, 0, 0],
[0, 0, 0, 0],
[0, 0, 0, 0],
[0, 1, 1, 0]]
goal = [0, len(grid[0]) - 1]
expected_value = [[57.903, 40.278, 26.066, 0.000],
[47.055, 36.572, 29.994, 27.270],
[53.172, 42.023, 37.775, 45.092],
[77.586, 1000., 1000., 73.546]]
expected_policy = [['>', 'v', 'v', '*'],
['>', '>', '^', '<'],
['>', '^', '^', '<'],
['^', ' ', ' ', '^']]
value, policy = homework._stochastic_value(grid, goal)
self.assertEqual(expected_policy, policy)
self.assertAlmostEqual(expected_value, value, 3)
