Shortcuts

DMControlEnv

torchrl.envs.libs.dm_control.DMControlEnv(*args, **kwargs)[source]

DeepMind Control lab environment wrapper.

Parameters:
  • env_name (str) – name of the environment

  • task_name (str) – name of the task

  • seed (int, optional) – seed to use for the environment

  • from_pixels (bool, optional) – if True, the observation will be returned as an image. Default is False.

Examples

>>> env = DMControlEnv(env_name="cheetah", task_name="run",
...    from_pixels=True, frame_skip=4)
>>> td = env.rand_step()
>>> print(td)
>>> print(env.available_envs)

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources