641a28fbf0daff0ad1ad0f43d2c4b545cb6f9656,examples/reinforcement_learning/tutorial_cartpole_ac.py,,,#,148

Before Change

for i_episode in range(MAX_EPISODE):
    episode_time = time.time()
    s = env.reset()
    t = 0  // number of step in this episode
    all_r = []  // rewards of all steps
    while True:
        if RENDER: env.render()

After Change

for i_episode in range(MAX_EPISODE):
    episode_time = time.time()
    s = env.reset().astype(np.float32)
    t = 0  // number of step in this episode
    all_r = []  // rewards of all steps
    while True:
        if RENDER: env.render()

Instances