Explanation Design in Strategic Learning: Sufficient Explanations that Induce Non-harmful Responses

With docker:

1. Run docker-compose -f dockerenv/docker-compose.yml up notebook.
2. Open the notebook file experiments/main.ipynb to run the main experiments.

With GCP:

1. Use the following parameter when creating a VM:

   image=projects/ml-images/global/images/c2-deeplearning-pytorch-2-4-cu124-v20241118-debian-11-py310
   

2. Install the additional python packages (if missing):

   ctgan==0.11.0
   lime==0.2.0.1
   git+https://github.com/openai/CLIP.git@dcba3cb2e2827b402d2701e7e1c7d9fed8a20ef1
   

3. Open the notebook file experiments/main.ipynb to run the main experiments.