def testActualLoad(self):
env = BatteryEnv(reward_func=reward_equationMAX)
self.assertEqual(len(env.actual_load_list), 0)
for i in range(10):
action = 0
observation, reward, done, info = env.step(action)
self.assertEqual(len(env.actual_load_list), 10)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.sum(), 158838.65)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.min(), 15226.48)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.max(), 16997.13)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.mean(), 15883.865)
env.restart_env()
self.assertEqual(len(env.actual_load_list), 0)
for i in range(10):
action = 1
observation, reward, done, info = env.step(action)
self.assertEqual(len(env.actual_load_list), 10)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.sum(), 159238.65)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.min(), 15326.48)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.max(), 16997.13)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.mean(), 15923.865)
env.restart_env()
self.assertEqual(len(env.actual_load_list), 0)
for i in range(10):
action = 2
observation, reward, done, info = env.step(action)
self.assertEqual(len(env.actual_load_list), 10)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.sum(), 159238.65)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.min(), 15326.48)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.max(), 16997.13)
arr = np.array(env.actual_load_list)
self.assertEqual(arr.mean(), 15923.865)
def testEnvIndex(self):
env = BatteryEnv(reward_func=reward_equationMAX)
self.assertEqual(env.state_idx, 0)
for i in range(10):
action = env.action_space.sample()
observation, reward, done, info = env.step(action)
self.assertEqual(env.state_idx, 10)
env.restart_env()
self.assertEqual(env.state_idx, 0)
def testCOND(self):
env = BatteryEnv(reward_func=reward_equationCOND)
lst = [1,2,3,3,10,-50]
self.assertEqual(env.reward_func(lst), 0)
def testLAST(self):
env = BatteryEnv(reward_func=reward_equationLAST)
lst = [1,2,3,3,10,-50]
self.assertEqual(env.reward_func(lst), -50)
def testSUM(self):
env = BatteryEnv(reward_func=reward_equationSUM)
lst = [1,2,3,3,10,-50]
self.assertEqual(env.reward_func(lst), -31)
def testMAX(self):
env = BatteryEnv(reward_func=reward_equationMAX)
lst = [1,2,3,3,10,-50]
self.assertEqual(env.reward_func(lst), 10)
def testEnvActionSpace(self):
env = BatteryEnv(reward_func=reward_equationMAX)
self.assertIn(env.action_space.sample(), [0, 1, 2])