Refactor the MADDPG and MATD3 algorithms based on the pettingzoo MPE(multi-agent patical env) environment.

[Ronchy2000]

Refactor the MADDPG and MATD3 algorithms based on the pettingzoo MPE environment, and overload the mpe environment to support custom environments!

Solve some problems, such as rendering problems.

Please check my repository: https://github.com/Ronchy2000/Multi-agent-RL/tree/master/MADDPG_Continous

Please feel free to raise PRs and questions for any questions!

感谢题主的贡献，此外想在这里推一下我做的一些工作。

重构基于pettingzoo MPE环境的MADDPG及MATD3算法，且重载mpe环境，支持自定义环境！

解决若干问题，如渲染问题等。

请查看我的仓库：https://github.com/Ronchy2000/Multi-agent-RL/tree/master/MADDPG_Continous

任何问题欢迎提PR和issue！