gym-dmc 0.2.0rc4

gym-dmc is a gym wrapper around DeepMind Control Suite domains.

Link to other OpenAI Gym Plugins:

• gym-sawyer

• gym-toy-nav

Usage pattern:

import gym

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

For the full list of environments, you can print:

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 patten in https://github.com/geyang/gym_dmc/blob/master/specs/test_gym_dmc.py:

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