新人，执行到“python test.py”这一步时，报如下错误，请问有好的解决办法吗？

[meici2023]

[tppig]

我也碰到了这个问题。最神奇的是我一开始能跑的，后来不知怎么的突然不能跑了。

重新装一下环境后又可以运行了。可以试一下重新建一个conda环境。

[IAAI-star]

我也是遇到了相似的问题，请问您的目前解决了么？ 我问了chatGPT，说是代码与模型不符，让我检查模型啥的，不懂，以下是报错的代码： (StreetFighterAI) C:\Users\jiaxin\StreetFighterAI\street-fighter-ai-master\main>python test.py Wrapping the env with a Monitor wrapper Wrapping the env in a DummyVecEnv. Wrapping the env in a VecTransposeImage. Traceback (most recent call last): File "test.py", line 53, in model = PPO.load(os.path.join(MODEL_DIR, MODEL_NAME), env=env) File "C:\Users\jiaxin.conda\envs\StreetFighterAI\lib\site-packages\stable_baselines3\common\base_class.py", line 641, in load model.set_parameters(params, exact_match=True, device=device) File "C:\Users\jiaxin.conda\envs\StreetFighterAI\lib\site-packages\stable_baselines3\common\base_class.py", line 574, in set_parameters attr.load_state_dict(params[name], strict=exact_match) File "C:\Users\jiaxin.conda\envs\StreetFighterAI\lib\site-packages\torch\nn\modules\module.py", line 2041, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for ActorCriticCnnPolicy: Unexpected key(s) in state_dict: "pi_features_extractor.cnn.0.weight", "pi_features_extractor.cnn.0.bias", "pi_features_extractor.cnn.2.weight", "pi_features_extractor.cnn.2.bias", "pi_features_extractor.cnn.4.weight", "pi_features_extractor.cnn.4.bias", "pi_features_extractor.linear.0.weight", "pi_features_extractor.linear.0.bias", "vf_features_extractor.cnn.0.weight", "vf_features_extractor.cnn.0.bias", "vf_features_extractor.cnn.2.weight", "vf_features_extractor.cnn.2.bias", "vf_features_extractor.cnn.4.weight", "vf_features_extractor.cnn.4.bias", "vf_features_extractor.linear.0.weight", "vf_features_extractor.linear.0.bias".

[XrbStudying]

我也遇到了相同的问题，重新建了虚拟环境还是不行，请问有什么解决方案吗？

/home/xrb280/anaconda3/envs/StreetFighterAI2/lib/python3.8/site-packages/stable_baselines3/common/save_util.py:166: UserWarning: Could not deserialize object observation_space. Consider using custom_objects argument to replace this object. Exception: __randomstate_ctor() takes from 0 to 1 positional arguments but 2 were given warnings.warn( Traceback (most recent call last): File "test.py", line 55, in model = PPO.load(os.path.join(MODEL_DIR, MODEL_NAME), env=env) File "/home/xrb280/anaconda3/envs/StreetFighterAI2/lib/python3.8/site-packages/stable_baselines3/common/base_class.py", line 678, in load raise KeyError("The observation_space and action_space were not given, can't verify new environments") KeyError: "The observation_space and action_space were not given, can't verify new environments"

[761046683]

我也是我也是，这个问题咋办呀，解决了滴滴我一下

[JizhiXiang]

如果KeyError: "The observation_space and action_space were not given, can't verify new environments"报错的话， 将test.py的52~53行换成如下即可解决：

# 参考https://github.com/linyiLYi/street-fighter-ai/issues/16#issuecomment-1515463967
# if not RANDOM_ACTION:
#     # 如果是你自己训练的模型    
#     model = PPO.load(os.path.join(MODEL_DIR, MODEL_NAME), env=env)
if not RANDOM_ACTION:
    # 如果你使用的是linyiLYi提供的模型
    keys = ['high', 'low', 'bounded_above', 'bounded_below']
    setattr(env.observation_space, '_shape', (3,100,128))
    for k in keys:
        new_attr = getattr(env.observation_space, k).reshape(3,100,128)
        setattr(env.observation_space, k, new_attr)
    model = PPO.load(os.path.join(MODEL_DIR, MODEL_NAME), env=env,
                custom_objects = {'observation_space': env.observation_space, 'action_space': env.action_space})