Feasible Policy Iteration

Code of the paper "Feasible Policy Iteration".
paper

Installation

mamba create -n fpi python=3.10
mamba activate fpi

pip install --upgrade "jax[cuda11_pip]" -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html

pip install safety-gymnasium

git clone https://github.com/yangyujie-jack/Feasible-Policy-Iteration.git
cd fpi
pip install -e .