Error when running the tutorial code

[WangJuan6]

Hi,
I run the tutorial code by python tutorial_PPO.py, but I got an error:

  Traceback (most recent call last):
  File "/data/projects/20240627/ElegantRL/helloworld/tutorial_PPO.py", line 65, in <module>
    train_ppo_for_pendulum(GPU_ID)
  File "/data/projects/20240627/ElegantRL/helloworld/tutorial_PPO.py", line 31, in train_ppo_for_pendulum
    train_agent(args)
  File "/data/projects/20240627/ElegantRL/helloworld/run.py", line 40, in train_agent
    buffer_items = agent.explore_env(env, horizon_len)
  File "/data/projects/20240627/ElegantRL/helloworld/agent.py", line 207, in explore_env
    state = torch.as_tensor(ary_state, dtype=torch.float32, device=self.device)
ValueError: expected sequence of length 3 at dim 1 (got 0)

To solve this problem, I change the code in agent.py:
change
state = torch.as_tensor(ary_state, dtype=torch.float32, device=self.device)
into
state = torch.as_tensor(ary_state[0], dtype=torch.float32, device=self.device)
but I got a new error:

Traceback (most recent call last):
  File "/data/projects/20240627/ElegantRL/helloworld/tutorial_PPO.py", line 65, in <module>
    train_ppo_for_pendulum(GPU_ID)
  File "/data/projects/20240627/ElegantRL/helloworld/tutorial_PPO.py", line 31, in train_ppo_for_pendulum
    train_agent(args)
  File "/data/projects/20240627/ElegantRL/helloworld/run.py", line 40, in train_agent
    buffer_items = agent.explore_env(env, horizon_len)
  File "/data/projects/20240627/ElegantRL/helloworld/agent.py", line 211, in explore_env
    ary_state, reward, done, _ = env.step(ary_action)
  File "/data/projects/20240627/ElegantRL/helloworld/env.py", line 24, in step
    state, reward, done, info_dict = self.env.step(action * 2)
ValueError: too many values to unpack (expected 4)

Can you help me to solve these problems?
Thanks