https://github.com/geyang/gym-dmc

DeepMind Control Suite plugin for gym
https://github.com/geyang/gym-dmc

Last synced: about 2 months ago
JSON representation

DeepMind Control Suite plugin for gym

• Host: GitHub
• URL: https://github.com/geyang/gym-dmc
• Owner: geyang
• License: mit
• Created: 2020-05-20T17:30:43.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2024-04-11T22:08:11.000Z (9 months ago)
• Last Synced: 2024-04-13T16:32:55.795Z (9 months ago)
• Language: Jupyter Notebook
• Size: 58.6 KB
• Stars: 5
• Watchers: 0
• Forks: 3
• Open Issues: 3
• Metadata Files:
  • Readme: README
  • License: LICENSE

Awesome Lists containing this project

README

        
``gym-dmc``, OpenAI Gym Plugin for DeepMind Control Suite

=========================================================

Link to other OpenAI Gym Plugins:

-  ``gym-sawyer``

-  ``gym-toy-nav``

Update Log

----------

-  **2024-03-25**: Return ``np.Array`` from ``env.render()`` function

-  **2022-01-13**: Add space_dtype for overriding the dtype for the

   state and action spaces. Default to None, need to set to

   ``float/np.float32`` for pytorch_SAC implementation.

-  **2022-01-11**: Added a ``env._get_obs()`` method to allow one to

   obtain the observation after resetting the environment. **Version:

   ``v0.2.1``**

Installation

------------

The ``dm_control`` dependency relies on lower versions of setuptools and

wheel. Downgrade to fix the installation error.

.. code-block:: shell

   pip install setuptools==65.5.0

   pip install wheel==0.38.4

   pip install gym-dmc

How To Use

----------

Usage pattern:

.. code-block:: python

   import gym

   env = gym.make("dmc:Pendulum-swingup-v1")

For the full list of environments, you can print:

.. code-block:: python

   from dm_control.suite import ALL_TASKS

   print(*ALL_TASKS, sep="\n")

   # Out[2]: ('acrobot', 'swingup')

   #         ('acrobot', 'swingup_sparse')

   ...

We register all of these environments using the following pattern:

   acrobot task “swingup_sparse” becomes

   ``dmc:Acrobot-swingup_sparse-v1``

You can see the usage pattern in

`https://github.com/geyang/gym_dmc/blob/master/specs/test_gym_dmc.py `__:

.. code-block:: python

   env = gym.make('dmc:Walker-walk-v1', frame_skip=4, space_dtype=np.float32)

   assert env.action_space.dtype is np.float32

   assert env.observation_space.dtype is np.float32

   env = gym.make('dmc:Walker-walk-v1', frame_skip=4)

   assert env._max_episode_steps == 250

   assert env.reset().shape == (24,)

   env = gym.make('dmc:Walker-walk-v1', from_pixels=True, frame_skip=4)

   assert env._max_episode_steps == 250

   env = gym.make('dmc:Cartpole-balance-v1', from_pixels=True, frame_skip=8)

   assert env._max_episode_steps == 125

   assert env.reset().shape == (3, 84, 84)

   env = gym.make('dmc:Cartpole-balance-v1', from_pixels=True, frame_skip=8, channels_first=False)

   assert env._max_episode_steps == 125

   assert env.reset().shape == (84, 84, 3)

   env = gym.make('dmc:Cartpole-balance-v1', from_pixels=True, frame_skip=8, channels_first=False, gray_scale=True)

   assert env._max_episode_steps == 125

   assert env.reset().shape == (84, 84, 1)

**Note, the ``max_episode_steps`` is calculated based on the

``frame_skip``.** All DeepMind control domains terminate after 1000

simulation steps. So for ``frame_skip=4``, the ``max_episode_steps``

should be 250.

Built with :heart: by Ge Yang