Discovering and Achieving Goals via World Models

Discovering and Achieving Goals via World Models

[Project Website] [Benchmark Code] [Video (2min)] [Oral Talk (13min)] [Paper]

Russell Mendonca*¹, Oleh Rybkin*², Kostas Daniilidis², Danijar Hafner^3,4, Deepak Pathak¹
(* equal contribution, random order)

¹Carnegie Mellon University
²University of Pennsylvania
³Google Research, Brain Team
⁴University of Toronto

Official implementation of the Lexa agent from the paper Discovering and Achieving Goals via World Models.

Setup

Create the conda environment by running :

conda env create -f environment.yml

Clone the lexa-benchmark repo, and modify the python path
export PYTHONPATH= /lexa:

Export the following variables for rendering
export MUJOCO_RENDERER=egl; export MUJOCO_GL=egl

Training

First source the environment : source activate lexa

For training, run :

export CUDA_VISIBLE_DEVICES=
   
      
python train.py --configs defaults 
    
      --task 
     
       --logdir 
      

      
     
    
   

where method can be lexa_temporal, lexa_cosine, ddl, diayn or gcsl
Supported tasks are dmc_walker_walk, dmc_quadruped_run, robobin, kitchen, joint

To view the graphs and gifs during training, run tensorboard --logdir

Bibtex

If you find this code useful, please cite:

@misc{lexa2021,
    title={Discovering and Achieving Goals via World Models},
    author={Mendonca, Russell and Rybkin, Oleh and
    Daniilidis, Kostas and Hafner, Danijar and Pathak, Deepak},
    year={2021},
    Booktitle={NeurIPS}
}

Acknowledgements

This code was developed using Dreamer V2 and Plan2Explore.