-
Notifications
You must be signed in to change notification settings - Fork 6
Description
Hi, @CrisSherban and @AleTM1 !Thank you very much for your work! I alse want to replace PID algorithm with Neural Networks!But there is not enough information about the program, and I don't know how to run it.
I run as this: python test_singleagent.py --exp ./results/save-hover-ppo-kin-pid-03.08.2022_17.26.52 --time 6 , but the erros like the following:
/.Python3.8/lib/python3.8/site-packages/stable_baselines3/common/vec_env/patch_gym.py:95: UserWarning: You loaded a model that was trained using OpenAI Gym. We strongly recommend transitioning to Gymnasium by saving that model again./.Python3.8/lib/python3.8/site-packages/stable_baselines3/common/base_class.py", line 739, in load
warnings.warn(
Traceback (most recent call last):
File "test_singleagent.py", line 84, in
model = PPO.load(path)
File "
model._setup_model()
File "/.Python3.8/lib/python3.8/site-packages/stable_baselines3/ppo/ppo.py", line 174, in _setup_model/.Python3.8/lib/python3.8/site-packages/stable_baselines3/common/on_policy_algorithm.py", line 135, in _setup_model
super()._setup_model()
File "
self.policy = self.policy_class( # type: ignore[assignment]
File "/.Python3.8/lib/python3.8/site-packages/stable_baselines3/common/policies.py", line 535, in init/.Python3.8/lib/python3.8/site-packages/stable_baselines3/common/policies.py", line 592, in _build
self._build(lr_schedule)
File "
self._build_mlp_extractor()
File "/home/bruce/.Python3.8/lib/python3.8/site-packages/stable_baselines3/common/policies.py", line 578, in _build_mlp_extractor
self.mlp_extractor = MlpExtractor(
File "/.Python3.8/lib/python3.8/site-packages/stable_baselines3/common/torch_layers.py", line 234, in init/.Python3.8/lib/python3.8/site-packages/torch/nn/modules/linear.py", line 99, in init
policy_net.append(nn.Linear(last_layer_dim_pi, curr_layer_dim))
File "
self.weight = Parameter(torch.empty((out_features, in_features), **factory_kwargs))
TypeError: empty() received an invalid combination of arguments - got (tuple, dtype=NoneType, device=NoneType), but expected one of:
- (tuple of ints size, *, tuple of names names, torch.memory_format memory_format = None, torch.dtype dtype = None, torch.layout layout = None, torch.device device = None, bool pin_memory = False, bool requires_grad = False)
- (tuple of ints size, *, torch.memory_format memory_format = None, Tensor out = None, torch.dtype dtype = None, torch.layout layout = None, torch.device device = None, bool pin_memory = False, bool requires_grad = False)