def test_get_reward(base_env: BaseEnv):
base_env.reset()
obs, reward, done, _ = base_env.step(4)
base_env.state.score_item = [10, 200, -500, 500]
assert reward == -0.01
assert base_env.get_reward() == 30
def test_step(base_env: BaseEnv):
base_env.reset()
obs, reward, done, _ = base_env.step(5)
assert reward == 0.01
assert not done
obs, reward, done, _ = base_env.step(2)
assert reward == -0.01
assert base_env.state.get_bomberman().get_direction() == 'East'
obs, reward, done, _ = base_env.step(2)
assert reward == -0.01
assert base_env.state.get_bomberman().get_direction() == 'East'
obs, reward, done, _ = base_env.step(2)
assert reward == -0.01
assert base_env.state.get_bomberman().get_direction() == 'East'
obs, reward, done, _ = base_env.step(4)
assert reward == -0.01
obs, reward, done, _ = base_env.step(4)
assert reward == 10
bomb = Bomb((3, 3))
bomb.countdown = 1
base_env.state.get_bombs().append(bomb)
obs, reward, done, _ = base_env.step(4)
assert reward == 80
assert done