h& "SrSSKJr SSKrSSKJr SSKrSSKr SSK J r SSK J r JrJr SSKr\\\R$4r/SQr\R,"\\"\5S 9r\R,"\\"\5S 9r"S S \ 5rg!\a \ "S5ef=f) zLHelper functions and wrapper class for converting between PyTorch and NumPy.) annotationsN)Union)DependencyNotInstalled)ArrayConversionarray_conversionmodule_namespacezcTorch is not installed therefore cannot call `torch_to_numpy`, run `pip install "gymnasium[torch]"`) NumpyToTorchtorch_to_numpynumpy_to_torchDevice)xpc4^\rSrSrSrSSU4SjjjrSrU=r$)r %aWraps a NumPy-based environment such that it can be interacted with PyTorch Tensors. Actions must be provided as PyTorch Tensors and observations will be returned as PyTorch Tensors. A vector version of the wrapper exists, :class:`gymnasium.wrappers.vector.NumpyToTorch`. Note: For ``rendered`` this is returned as a NumPy array not a pytorch Tensor. Example: >>> import torch >>> import gymnasium as gym >>> env = gym.make("CartPole-v1") >>> env = NumpyToTorch(env) >>> obs, _ = env.reset(seed=123) >>> type(obs) >>> action = torch.tensor(env.action_space.sample()) >>> obs, reward, terminated, truncated, info = env.step(action) >>> type(obs) >>> type(reward) >>> type(terminated) >>> type(truncated) Change logs: * v1.0.0 - Initially added cB>[TU]U[[US9 X lg)zWrapper class to change inputs and outputs of environment to PyTorch tensors. Args: env: The NumPy-based environment to wrap device: The device the torch Tensors should be moved to )envenv_xp target_xp target_deviceN)super__init__nptorchdevice)selfrr __class__s [/home/james-whalen/.local/lib/python3.13/site-packages/gymnasium/wrappers/numpy_to_torch.pyrNumpyToTorch.__init__Es  SuFS%+ )r)N)rzgym.Envrz Device | None)__name__ __module__ __qualname____firstlineno____doc__r__static_attributes__ __classcell__)rs@rr r %s> , ,rr )r# __future__r functoolstypingrnumpyr gymnasiumgymgymnasium.errorr#gymnasium.wrappers.array_conversionrrrrstrrr ImportError__all__partialr r r rrr3sR"2 3 $ %F I""#38H8LM""#38H8OP),?), m s A??B