erob123 / interpretable_marl Goto Github PK

1. Create conda environment: conda create -n interpretable_marl python=3.7

2. Activate conda environment: conda activate interpretable_marl

3. Install GPU deps: conda install -c conda-forge cudatoolkit=11.2.2 cudnn=8.1.0 (https://gretel.ai/blog/install-tensorflow-with-cuda-cdnn-and-gpu-support-in-4-easy-steps)

4. Save library path for gpu deps:

   mkdir -p $CONDA_PREFIX/etc/conda/activate.d
   echo 'export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CONDA_PREFIX/lib/' > $CONDA_PREFIX/etc/conda/activate.d/env_vars.sh
   

5. Close and reopen terminal or SSH and reactivate conda environment if needed

6. Move into the root project directory: cd interpretable_marl (not interpretable_marl/interpretable_marl)

7. Clone overcooked_ai: git clone https://github.com/HumanCompatibleAI/overcooked_ai.git (not using git submodules since only one repo, but if we add more, we should use submodules)

8. Install overcooked : pip install -e overcooked_ai/

9. Install poetry: pip install poetry

10. Install the root project with poetry: poetry install

11. Open & run the notebook tutorial in overcooked to verify the upstream overcooked setup works

1. Login to wandb: wandb login
2. Run python interpretable_marl/run_single.py to verify the interpretable_marl setup works
3. Edit or run experiments as desired

TODO: Add instructions for editing model, augmenting state in both training and evaluation, running experiments, changing action verbiage, debugging, changing config, etc.