Responsive Safety in Reinforcement Learning by PID Lagrangian Methods

Based on https://arxiv.org/abs/2007.03964

Setup

• Clone this repository: git clone …
• open Anaconda Prompt and type conda create -n tensorflow python=3.6
• type conda activate tensorflow to active the virtual environment
• enter the folder where requirements.txt is in Anaconda Prompt
• Execute pip install -r requirement.txt to to start downloading the required modules

Run

• enter pycharm, choose edit Configuration, choose python interpreter as the virtual environment that you just created.
• run "run.py"