There is no need for compilation. You can install all requirements using Pip, however, you might prefer to install some manully, including:
# TODO: create and activate your virtual env of choice
# download the repo as well as the submodules (including )
git clone https://github.com/UBCMOCCA/SymmetricRL --recurse-submodules
cd SymmetricRL
pip install -r requirements # you might prefer to install some packages (including PyTorch) yourselfThere is also a helper script in setup/setup_cc.sh that can be used to install the requirements on Compute Canada.
To run an experiment named test_experiment with the PyBullet humanoid environment you can run:
./scripts/local_run_playground_train.sh w2_test_experiment env_name='pybullet_envs:Walker2DBulletEnv-v0'
# run the same experiment with the NET architecture symmetry method (other options include "traj, loss, phase, net2")
./scripts/local_run_playground_train.sh w2_net_experiment env_name='pybullet_envs:Walker2DBulletEnv-v0' mirror_method='net'The w2_net_experiment is the name of the experiment. This command will create a new experiment directory inside the runs directory that contains the following files:
pid: the process ID of the task running the training algorithmprogress.csv: a CSV file containing the data about the the training progressslurm.out: the output of the process. You can usetail -fto view the contentsconfigs.json: a JSON file containing all the hyper-parameter values used in this runrun.json: extra useful stuff about the run including the host information and the git commit ID (only works if GitPython is installed)models: a directory containing the saved models
In case you use Compute Canada you also use the other scripts like cedar_run_playground_train.sh to create a batch job. These scripts use the same argument sctructure but also allow you to run the same task with multiple replicates using the num_replicates variable.
The plot_from_csv.py script can be helpful for plotting the learning curves:
python -m playground.plot_from_csv --load_paths runs/*/*/ --columns mean_rew max_rew --smooth 2
# to group the results based on the name
python -m playground.plot_from_csv --load_paths runs/*/*/ --columns mean_rew max_rew --name_regex ".*__([^_\/])*" --group 1- The
load_pathsargument specifies which directories the script should look into - It opens the
progress.csvfile and plots thecolumnsas the y-axis and uses therowfor the x-axis (defaults tototal_num_steps) - You can also provide a
name_regexto make the figure legends simpler and more readable, e.g.--name_regex 'walker-(.*)mirror\/'would turnruns/2019_07_08__23_53_20__walker-lossmirror/1to simplyloss. groupcan be used to aggregate the results of multiple runs of the same experiment into one.name_regexis used to specify the groups.
The enjoy.py script can be used to run a learned policy and render the results:
python -m playground.enjoy with experiment_dir=runs/<EXPERIMENT_DIRECTORY>
# plot the joint positions over time
python -m playground.evaluate with experiment_dir=runs/<EXPERIMENT_DIRECTORY> plot=TrueThe evaluate.py script is used for evaluating learned policies. The results will be saved to a new file called evaluate.json inside the experiment_dir where the policy was loaded from.
# evaluate with 10000 steps
python -m playground.evaluate with experiment_dir=runs/<EXPERIMENT_DIRECTORY> max_steps=10000
# with rendering
python -m playground.evaluate with experiment_dir=runs/<EXPERIMENT_DIRECTORY> render=True
# evaluate all experiments
for d in runs/*/*/; do python -m playground.evaluate with experiment_dir=$d; doneMetrics (will be expanded):
- Symmetric Index (joint angle and torque)
- Uses the
MetricsEnvenvironment wrapper fromsymmetric/metric_utils.py
- Uses the
NOTE: the current script assumes that the environment has a similar interface to PyBullet locomotion environments. It assumes the following parameters are present in the unwrapped environment:
robot.feet_contactrobot.ordered_joints- The joint names that have the word
leftin them are assumed to be on the left side. Any other joint that does not contain the wordabdomenis assumed to be on the right side.
- The joint names that have the word
The environments that are currently tested and supported:
Walker2DBulletEnvHumanoidBulletEnvWalker3DCustomEnvWalker3DStepperEnv
Please cite the following paper if you found our work useful. Thanks!
Farzad Adbolhosseini and Hung Yu Ling and Zhaoming Xie and Xue Bin Peng and Michiel van de Panne. "On Learning Symmetric Locomotion", Proc. ACM SIGGRAPH Motion, Interaction, and Games (MIG 2019).
@inproceedings{2019-MIG-symmetry,
title={On Learning Symmetric Locomotion},
author={Farzad Adbolhosseini and Hung Yu Ling and Zhaoming Xie and Xue Bin Peng and Michiel van de Panne},
booktitle = {Proc. ACM SIGGRAPH Motion, Interaction, and Games (MIG 2019)},
year={2019}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent