Skip to content

taochenshh/block_stacking

Repository files navigation

Robot Construction via Planning and Learning

Install Mujoco

  1. Download mjpro150 linux here: https://www.roboti.us/index.html and apply for a license.
  2. Unzip the downloaded mjpro150 directory into ~/.mujoco/mjpro150, and place your license key(mjkey.txt) at ~/.mujoco/mjkey.txt
  3. add export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:~/.mujoco/mjpro150/bin to ~/.bashrc
  4. add export LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libGLEW.so:/usr/lib/nvidia-384/libGL.so to ~/.bashrc
  5. sudo apt-get install libosmesa6-dev (if you are on local machine)
  6. cd mujoco
  7. pip install -r requirements.txt
  8. python setup.py install
  9. python examples/body_interaction.py

Note:

  • If you wanna use viewer.render, you need to set LD_PRELOAD to /usr/lib/x86_64-linux-gnu/libGLEW.so:/usr/lib/nvidia-384/libGL.so. However, if you wanna use sim.render, you need to unset it (unset LD_PRELOAD).

Usage:

python save_bk_imgs.py
python split_train_test.py
python train_stability_checker.py
python test_stability_checker.py
python tests/test.py
python tests/test_vis.py

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages