HPCC2025/human_action.py
2025-03-22 09:47:52 +08:00

19 lines
381 B
Python

from env import PartitionMazeEnv
# from env_dis import PartitionMazeEnv
env = PartitionMazeEnv()
state = env.reset()
print(state)
action_series = [[0.67], [0], [0], [0], [0.7]]
# action_series = [0, 0, 3, 0, 10]
for i in range(100):
action = action_series[i]
state, reward, done, info, _ = env.step(action)
print(state)
print(reward)
if done:
break