RoboHive is a collection of environments/tasks simulated with the MuJoCo physics engine exposed using the OpenAI-Gym API.
Getting started with RoboHive is as simple as -
# Install RoboHive and demo an environemnt
pip install robohive
python -m robohive.utils.examine_env -e FrankaReachRandom-v0or, alternatively,
git clone --recursive https://github.com/vikashplus/robohive.git; cd robohive
pip install -e .
python -m robohive.utils.examine_env -e FrankaReachRandom-v0See detailed installation instructions for options on mujoco-python-bindings and visual-encoders (R3M, RRL, VC), and frequently asked questions for more details.
RoboHive contains a variety of environement, which are organized as suites. Each suites is a collection of loosely related environements. Following suites are provided at the moment with plans to improve the diversity of the collection.
This suite contains a collection of environement centered around dexterous manipulation. Standard ADROIT benchmarks introduced in Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations, RSS2018.) are a part of this suite
This suite contains a collection of environement centered around Arm+Gripper manipulation.
This suite contains a collection of environements related to biomechanics. Standard MyoSuite benchmarks are a part of this suite
This suite contains a collection of environement centered around multi-tassk. Standard RelayKitchen benchmarks are a part of this suite
This suite contains a collection of environement centered around dexterous manipulation. Standard TCDM benchmarks are a part of this suite
This suite contains a collection of environement centered around real world locomotion and manipulation. Standard ROBEL benchmarks are a part of this suite