pip install gym==0.12.1
cd diagnostic_experiments/
python main_fixpol.py --multi_option # for experiments with fixed options
python main.py --multi_option # for experiments with learned options

virtualenv moc_cc --python=python3
source moc_cc/bin/activate
pip install tensorflow==1.12.0 
cd continuous_control
pip install -e . 
pip install gym==0.9.3
pip install mujoco-py==0.5.1

cd baselines/ppoc_int
python run_mujoco.py --switch --nointfc --env AntWalls --eta 0.9 --mainlr 8e-5 --intlr 8e-5 --piolr 8e-5

virtualenv moc_vision --python=python3
source moc_vision/bin/activate
pip install tensorflow==1.13.1
cd vision_miniworld
pip install -e .
pip install gym==0.15.4

cd baselines/
# Run agent in first task
python run.py --alg=ppo2_options --env=MiniWorld-WallGap-v0 --num_timesteps 2500000 --save_interval 1000  --num_env 8 --noptions 4 --eta 0.7

# Load and run agent in transfer task
python run.py --alg=ppo2_options --env=MiniWorld-WallGapTransfer-v0 --load_path path/to/model --num_timesteps 2500000 --save_interval 1000  --num_env 8 --noptions 4 --eta 0.7

@inproceedings{
klissarov2021flexible,
title={Flexible Option Learning},
author={Martin Klissarov and Doina Precup},
booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},
year={2021},
url={https://openreview.net/forum?id=L5vbEVIePyb}
}