def test_error_if_col_full():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[2, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0],
[2, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0],
[2, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0],
]
)
with pytest.raises(ValueError):
under_test.step(0)
def test_step_return_values_win():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[2, 2, 2, 0, 0, 0, 0],
[1, 1, 1, 0, 0, 0, 0],
]
)
expected_observation = np.array(
[
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[2, 2, 2, 0, 0, 0, 0],
[1, 1, 1, 1, 0, 0, 0],
]
)
expected_reward = 100.0
expected_done = True
expected_info = {}
observation, reward, done, info = under_test.step(3)
assert np.array_equal(observation, expected_observation)
assert expected_reward == reward
assert expected_done == done
assert expected_info == info
def test_step():
under_test = ConnectFourGame()
expected = np.array(
[
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0],
]
)
under_test.step(0)
assert np.array_equal(under_test.board, expected)
assert under_test.turn == "O"
def test_reset():
under_test = ConnectFourGame()
expected = np.array(
[
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
]
)
# Do some stuff
under_test.step(1)
under_test.step(2)
under_test.step(1)
under_test.step(4)
under_test.reset()
assert np.array_equal(under_test.board, expected)
def test_step_return_values_draw():
under_test = ConnectFourGame()
under_test.board = np.array(
[
[0, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[1, 2, 1, 1, 2, 1, 2],
[1, 2, 1, 1, 2, 1, 1],
[1, 2, 1, 1, 2, 1, 2],
]
)
under_test.turn = "O"
expected_observation = np.array(
[
[2, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[2, 1, 2, 2, 1, 2, 1],
[1, 2, 1, 1, 2, 1, 2],
[1, 2, 1, 1, 2, 1, 1],
[1, 2, 1, 1, 2, 1, 2],
]
)
expected_reward = -50.0
expected_done = True
expected_info = {}
observation, reward, done, info = under_test.step(0)
assert np.array_equal(observation, expected_observation)
assert expected_reward == reward
assert expected_done == done
assert expected_info == info
def test_step_return_values():
under_test = ConnectFourGame()
expected_observation = np.array(
[
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0],
]
)
expected_reward = 0.0
expected_done = False
expected_info = {}
observation, reward, done, info = under_test.step(0)
assert np.array_equal(observation, expected_observation)
assert expected_reward == reward
assert expected_done == done
assert expected_info == info