Skip to content
Learning multi-agent policies for flocking using graph neural networks
Python
Branch: master
Clone or download

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
cfg cleaning Jul 24, 2019
learner cleaning Jul 24, 2019
models cleaning Jul 24, 2019
.gitignore removed results folder Sep 10, 2019
LICENSE Create LICENSE Jul 27, 2019
README.md cleaning Jul 24, 2019
airsim_test.py plotting Jul 2, 2019
flocking_gym_test.py tw flocks Jun 19, 2019
test_model.py cleaning Jul 24, 2019
test_model_transfer.py test airsim Jun 27, 2019
train.py transfer test code Jun 15, 2019

README.md

Learning Multi-Agent Policies using GNNs

Dependencies

Available algorithms:

  • Behavior Cloning as described in ArXiv 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
You can’t perform that action at this time.