# deepmind_MAS_enviroment

**Repository Path**: jasper_han/deepmind_MAS_enviroment

## Basic Information

- **Project Name**: deepmind_MAS_enviroment
- **Description**: github搬运工, 此处scipy需要0.19以下的版本
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: https://github.com/wwxFromTju/deepmind_MAS_enviroment
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-08-23
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

This repositories support the env in 《Multi-agent Reinforcement Learning in Sequential Social Dilemmas》 and 《Value-Decomposition Networks For Cooperative Multi-Agent Learning》.

hope can help people to research.


## enviroment
<img src="/gif/gathering.gif" width="500" height="100"/>
gathering

<img src="/gif/fetch.gif" width="500" height="100"/>
fetch

<img src="/gif/checkers.gif" width="500" height="100"/>
checkers

<img src="/gif/switchlevel0.gif" width="500" height="100"/>
switch level 0

<img src="/gif/switchlevel1.gif" width="500" height="100"/>
switch level 1

<img src="/gif/switchlevel2.gif" width="500" height="100"/>
switch level 2

## Citing
If you use this env in your research, you can cite it as follows:
```bibtex
@article{wang2018towards,
  title={Towards Cooperation in Sequential Prisoner's Dilemmas: a Deep Multiagent Reinforcement Learning Approach},
  author={Wang, Weixun and Hao, Jianye and Wang, Yixi and Taylor, Matthew},
  journal={arXiv preprint arXiv:1803.00162},
  year={2018}
}
```