Skip to content

mktk1117/raisimGym

 
 

Repository files navigation

raisimGym: RL examples using raisim

What is raisimGym

raisimGym is an example of a gym environment using raisim. It uses stable-baselines (https://github.com/hill-a/stable-baselines) for training and pybind11 (https://github.com/pybind/pybind11) for wrapping raisim in python.

News

  • There was a bug in the examples. The P gain was set to a wrong dimension. This is fixed as of v0.3.2. Please update to the latest version. If you used the example as a template for your project, please fix your project as well.

Requirements

Install

Please install/save everything locally to prevent corrupting your system files. We will assume that you have a single workspace where you save all repos related to raisim.

Here we introduce two variables

  • WORKSPACE: workspace where you clone your git repos
  • LOCAL_BUILD: build directory where you install exported cmake libraries

You can check out our docker file if you are stuck.

Python setup

  1. Install python3
    • For Ubuntu18.04 (sudo apt-get install -y cmake python3.6-dev python3-pip libpython3.6-dev)
    • For Ubuntu16.04 (sudo apt-get install -y cmake python3.5-dev python3-pip libpython3.5-dev)
  2. Setup your python environment (virtualenv or conda) with Python > 3.5

Dependencies

Install the following dependencies

Now install pybind11 as following

cd $WORKSPACE
git clone https://github.com/pybind/pybind11.git
cd pybind11 && git checkout v2.3 && mkdir build && cd build
cmake .. -DCMAKE_INSTALL_PREFIX=$LOCAL_BUILD -DPYBIND11_TEST=OFF
make install -j4

You might have to add LOCAL_BUILD/lib to your $LD_LIBRARY_PATH to ensure that ld finds Ogre3D shared objects.

Workflow

  1. Compile your c++ environment (instructions followed)
  2. Run your learning script (instructions followed)

or use the dockerfile provided (instruction below)

Compile

Set your compiler to g++>6.0 as following

export CXX=/usr/bin/g++-8 && export CC=/usr/bin/gcc-8

Now compile raisimGym as

python3 setup.py install --CMAKE_PREFIX_PATH LOCAL_BUILD --env /WHERE/YOUR/CUSTOM/ENVIRONMENT/IS

The "--env" directory should include a file called "Environment.hpp" which contains ENVIRONMENT class.

Compiling examples

We provide a shortcut for building examples. Replace $EXAMPLE_NAME by one of the following names: anymal, laikago, and quadrotor

python3 setup.py install --CMAKE_PREFIX_PATH $LOCAL_BUILD --env $EXAMPLE_NAME

Run

You can make your own runner. To use the example runner,

python3 scripts/anymal_blind_locomotion.py

Using raisimGym in Docker

  1. Install docker and Nvidia-docker2 (instruction).
  2. Build an image docker build -t raisim_gym $WORKSPACE/raisimGym/dockers/gpu
  3. Create a container using the provided docker runner $WORKSPACE/raisimGym/dockers/gpu/runner.bash
  4. Inside the container, compile your environment and execute your runner

Tutorial

Dr. Inkyu Sa kindly provided a comphensive tutorial on raisimGym here

Examples of trained policies

ANYmal

  • Trained with RTX 2080 + Intel 8700K + PPO [1]
  • 18 dof quadrupedal robot, 34-dimentional observation space
Initial policy 38 seconds of training
alt-text-1 alt-text-2
76 seconds of training 112 seconds of training
alt-text-1 alt-text-2

Quadrotor

This quadrotor example is not fully tuned for real applications. Please feel free to optimize the example alt-text-1

Notes

  • Due to conversion between numpy and eigen, the interface class (e.g., VectorizedEnv) should use row major matrices only.

Common issues and workarounds

  • When build fails, try again after deleting the build folder

How to contribute?

raisimGym is meant to be a minimal example. Please do not submit a pull request that contains features targeting specific applications. Bug fix/code clean-up are welcome.

Fork the repo, make changes and then send a pull request. Instructions can be found here

References

[1] Schulman, John, et al. "Proximal policy optimization algorithms." arXiv preprint arXiv:1707.06347 (2017).

Contributors

Jemin Hwangbo is developing/manaing raisimGym with help from the followig contributors

  • Inkyu Sa
  • Haloted

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 93.2%
  • Dockerfile 4.2%
  • Shell 1.4%
  • CMake 1.2%