Skip to content
Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"
Python Shell
Branch: master
Clone or download
Latest commit d39edfa Jul 16, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
envs initial commit Feb 15, 2019
src initial commit Feb 15, 2019
.gitignore initial commit Feb 15, 2019
LICENSE initial commit Feb 15, 2019
README.md update readme Jul 16, 2019

README.md

Learning to Control Self-Assembling Morphologies

Winner of Virtual Creatures Competition at GECCO 2019, Prague

[Project Website] [Demo Video]

Deepak Pathak*, Chris Lu*, Trevor Darrell, Phillip Isola, Alexei A. Efros
University of California, Berkeley
MIT

This is a pytorch based implementation for our paper on learning to control self-assembling agents using deep reinforcement learning. We investigate a modular co-evolution strategy: a collection of primitive agents learns to dynamically self-assemble into composite bodies while also learning to coordinate their behavior to control these bodies. We learn compositional policies to demonstrate better zero-shot generalization. If you find this work useful in your research, please cite:

@inproceedings{pathak19assemblies,
    Author = {Pathak, Deepak and Lu, Chris and Darrell, Trevor and
              Isola, Phillip and Efros, Alexei A.},
    Title = {Learning to Control Self-Assembling Morphologies:
              A Study of Generalization via Modularity},
    Booktitle = {arXiv preprint arXiv:1902.05546},
    Year = {2019}
}

Installation and Usage

  1. Setting up repository
git clone https://github.com/pathak22/modular-assemblies.git
cd modular-assemblies/
git clone https://github.com/Unity-Technologies/ml-agents.git
cd ml-agents/
git reset --hard 6c5255e
cd ..
bash envs/setup_env.sh

python3 -m venv assemblyEnv
source $PWD/assemblyEnv/bin/activate
pip install --upgrade pip
  1. Installation

    • Requirements:
      • CUDNN-5.1, CUDA-8.0, Python-3.5
    • Detailed setup, skip to quick setup for exact replication:
    # Install Pytorch from http://pytorch.org/
    pip install http://download.pytorch.org/whl/cu80/torch-0.3.0.post4-cp35-cp35m-linux_x86_64.whl
    pip install torchvision
    pip install --upgrade visdom
    
    # Install baselines for Atari preprocessing
    pip install gym==0.9.4 # baselines install latest gym first automatically, but latest gym has moved to mujoco5 so first install old gym and then install baselines
    git clone https://github.com/openai/baselines.git
    cd baselines
    git reset --hard b5be53d
    pip install -e .
    
    # Additional packages
    pip install numpy
    pip install matplotlib
    pip install pillow
    pip install opencv-python
    
    # fold
    cd modular-assemblies/src/
    git clone https://github.com/nearai/pytorch-tools.git
    cd pytorch-tools/
    git reset --hard 09dccb2
    python setup.py install
    • Quick setup for exact replication:
    pip install -r requirements.txt
  2. Run code

cd modular-assemblies/src/
python test_env.py

Acknowledgement

Builds upon Ilya Kostrikov's Pytorch PPO implementation.

You can’t perform that action at this time.