HPCC2025/human_action.py

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