def test_environment_actions():
"""Tests environment is executing actions correctly"""
env = Bit_Flipping_Environment(5)
env.reset()
env.state = [1, 0, 0, 1, 0, 1, 0, 0, 1, 0]
env.step(0)
env.state = env.next_state
assert env.state == [0, 0, 0, 1, 0, 1, 0, 0, 1, 0]
env.step(0)
env.state = env.next_state
assert env.state == [1, 0, 0, 1, 0, 1, 0, 0, 1, 0]
env.step(3)
env.state = env.next_state
assert env.state == [1, 0, 0, 0, 0, 1, 0, 0, 1, 0]
env.step(6)
env.state = env.next_state
assert env.state == [1, 0, 0, 0, 0, 1, 0, 0, 1, 0]
def test_environment_goal_achievement():
"""Tests environment is registering goal achievement properly"""
env = Bit_Flipping_Environment(5)
env.reset()
env.state = [1, 0, 0, 1, 0, 0, 0, 0, 0, 0]
env.desired_goal = [0, 0, 0, 0, 0]
env.step(0)
assert env.reward == -1
env.state = env.next_state
assert env.achieved_goal == [0, 0, 0, 1, 0]
env.step(2)
assert env.reward == -1
env.state = env.next_state
assert env.achieved_goal == [0, 0, 1, 1, 0]
env.step(2)
assert env.reward == -1
env.state = env.next_state
assert env.achieved_goal == [0, 0, 0, 1, 0]
env.step(3)
assert env.reward == 5