init_parameters function throws an error

[Ojigrande]

Description

Hello.
For my experiments I use nvcr.io/nvidia/pytorch:24.01-py3 docker.

I have tried to run torch_gymnasium_cartpole_dqn.py example.
But when model.init_parameters(method_name="normal_", mean=0.0, std=0.1) method executes I have got the error:
ValueError: Attempted to use an uninitialized parameter in <function normal_ at 0x74bc340b0700>. This error happens when you are using a `LazyModule` or explicitly manipulating `torch.nn.parameter.UninitializedParameter` objects. When using LazyModules Call `forward` with a dummy batch to initialize the parameters before calling torch functions

What skrl version are you using?

1.3.0

What ML framework/library version are you using?

PyTorch 2.2.0a0+81ea7a4

Additional system information

Python 3.10.12

[Toni-SM]

Hi @Ojigrande

Thanks for reporting it, I see the issues... In the toni/space_tensor_conversion branch, I am working on generic spaces utils that will allow to initialize lazy torch models in Runner instances.

The solution will be to call the instantiated models

skrl/skrl/utils/runner/torch/runner.py

Line 255 in 2bd3b7a

return models

with a space sample

skrl/skrl/utils/spaces/torch/spaces.py

Line 240 in 17c6f11

def sample_space(space: spaces.Space, batch_size: int = 1, backend: str = Literal["numpy", "torch"], device = None) -> Any:

before returning them.