blob: 3002a5304da811f5dce2c1fd85a24b18ac2b6965 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
|
import gym
import time
from datetime import datetime
from stable_baselines3 import PPO
from stable_baselines3.common.vec_env import DummyVecEnv
from stable_baselines3.common.evaluation import evaluate_policy
env_name = 'CartPole-v1'
env = gym.make(env_name)
episodes = 5
for episode in range(1, episodes + 1):
state = env.reset()
done = False
score = 0
while not done:
env.render()
action = env.action_space.sample()
n_state, reward, done, info = env.step(action)
print(reward, done)
score += reward
# time.sleep(0.5)
now = datetime.now().strftime('%H:%M:%S')
print('{}, Episode:{} Score:{}'.format(now, episode, score))
env.close()
|
