HPCC2025/human_action.py
weixin_46229132 2362de4c54 修改dqn
2025-03-19 01:04:03 +08:00

17 lines
337 B
Python

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