Skip to content

katetolstaya/multiagent_gnn_policies

master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
cfg
Jul 24, 2019
Jul 24, 2019
Jul 24, 2019
Jul 27, 2019
Jul 2, 2019
Jul 24, 2019

Learning Multi-Agent Policies using GNNs

Dependencies

Available algorithms:

  • Behavior Cloning python3 train.py cfg/cloning.cfg
  • DAGGER imitation learning python3 train.py cfg/dagger.cfg

To test:

  • python3 test_model.py cfg/dagger.cfg

Other code:

  • python3 flocking_gym_test.py provides test code for the Gym Flock environments

Citing the Project

To cite this repository in publications:

@inproceedings{tolstaya2020learning,
  title={Learning decentralized controllers for robot swarms with graph neural networks},
  author={Tolstaya, Ekaterina and Gama, Fernando and Paulos, James and Pappas, George and Kumar, Vijay and Ribeiro, Alejandro},
  booktitle={Conference on Robot Learning},
  pages={671--682},
  year={2020}
}

About

Learning multi-agent policies for flocking using graph neural networks

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages