15 lines
400 B
Python
15 lines
400 B
Python
from env import PartitionMazeEnv
|
|
|
|
env = PartitionMazeEnv()
|
|
|
|
state = env.reset()
|
|
print(state)
|
|
|
|
action_series = [[0], [0.5], [0], [0.2], [0.4], [0.7], [0.3], [0.8], [0.5], [0.1], [0.7], [0.7], [0.9], [0.9], [0.1], [0.9], [0.9], [0.1]]
|
|
|
|
for i in range(100):
|
|
action = action_series[i]
|
|
state, reward, done, info, _ = env.step(action)
|
|
print(state, reward, done, info)
|
|
if done:
|
|
break |