mj_envs
is a collection of environments/tasks simulated with the Mujoco physics engine and wrapped in the OpenAI gym
API.
mj_envs
uses git submodules to resolve dependencies. Please follow steps exactly as below to install correctly.
- Clone this repo with pre-populated submodule dependencies
$ git clone --branch stable --recursive https://github.com/vikashplus/mj_envs.git
- Install package using
pip
$ cd mj_envs
$ pip install -e .
OR
Add repo to pythonpath by updating ~/.bashrc
or ~/.bash_profile
export PYTHONPATH="<path/to/mj_envs>:$PYTHONPATH"
- You can visualize the environments with random controls using the command below
$ python utils/visualize_env.py --env_name hammer-v0
NOTE: If the visualization results in a GLFW error, this is because mujoco-py
does not see some graphics drivers correctly. This can usually be fixed by explicitly loading the correct drivers before running the python script. See this page for details.
mj_envs contains a variety of environements, which are organized as modules. Each module is a collection of loosely related environements. Following modules are provided at the moment with plans to improve the diversity of the collection.
HMS contains a collection of environements centered around dexterous manipulation with anthroporphic 24 degrees of freedom Adroit Hand. These environments were designed for the publication: Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations, RSS2018.
Hand-Manipulation-Suite Tasks (video) |
---|