Comparing centralized and decentralized actor-critic and option-critic variants for MARL. Further details can be found in the projet paper in this repository. https://github.com/atharvaw1/CS5180-project/blob/main/RL_Project_Paper.pdf
Make a local virtual environment with the following command:
python3 -m venv venv
pip install -r requirements.txt
The four room single agent navigation task
Environments can be found on https://pettingzoo.farama.org/environments/mpe/
@article{lowe2017multi, title={Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments}, author={Lowe, Ryan and Wu, Yi and Tamar, Aviv and Harb, Jean and Abbeel, Pieter and Mordatch, Igor}, journal={Neural Information Processing Systems (NIPS)}, year={2017} }