Sequential rollout with Sequential value estimation (SrSv)

This is the official implementation of SrSv.

Installation

Dependences

conda create --name srsv python==3.9
pip install -r requirements.txt

Multi-agent MuJoCo

Following the instructios in https://github.com/openai/mujoco-py and https://github.com/schroederdewitt/multiagent_mujoco to setup a mujoco environment. In the end, remember to set the following environment variables:

LD_LIBRARY_PATH=${HOME}/.mujoco/mujoco200/bin;
LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libGLEW.so

StarCraft II & SMAC

Run the script

bash install_sc2.sh

Or you could install them manually to other path you like, just follow here: https://github.com/oxwhirl/smac.

How to run

When your environment is ready, you could run shells in the "scripts" folder. For example:

./train_smac.sh  

If you would like to change the configs of experiments, you could modify sh files or look for config.py for more details.

Citation

🌟 If you find this resource helpful, please consider starting this repository and cite our research:

@inproceedings{wan2025srsv,
  title={SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning},
  author={Wan, Xu and Yang, Chao and Yang, Cheng and Song, Jie and Sun, Mingyang},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={22},
  pages={23333--23342},
  year={2025}
}