def test_reward():
bit_flip = BitFlip(2)
bit_flip.state = np.array([0, 0])
bit_flip.goal = np.array([1, 0])
_, reward, _, _ = bit_flip.step(1)
assert reward == -1
def test_reward_expected_success():
bit_flip = BitFlip(2)
bit_flip.state = np.array([0, 0])
bit_flip.goal = np.array([1, 0])
_, reward, terminate, _ = bit_flip.step(0)
assert reward == 0
assert terminate == True