The code for CasualRL experiment

The maze environment is based on https://github.com/MattChanTK/gym-maze.
MinGrid world: https://github.com/Farama-Foundation/MiniGrid
The PPO/hPPO implement is based on https://github.com/onopkosonja/ReinforcementLearning.git
The hDQN implement is based on https://github.com/gmargo11/hDQN.git https://github.com/transedward/pytorch-hdqn.git The keybox is developed based on https://github.com/Farama-Foundation/gym-examples.git and inspired by paper Zheng Z, Oh J, Hessel M, et al. What can learned intrinsic rewards capture?[C]//International Conference on Machine Learning. PMLR, 2020: 11436-11446.

The gym environment creating example: https://www.gymlibrary.dev/content/environment_creation/ (This site is usually out of service)

The install tips in that site:
This documentation overviews creating new environments and relevant useful wrappers, utilities and tests included in Gym designed for the creation of new environments. You can clone gym-examples to play with the code that are presented here. We recommend that you use a virtual environment:
git clone https://github.com/Farama-Foundation/gym-examples
cd gym-examples
python -m venv .env
source .env/bin/activate
pip install -e .