论文原文:The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games
参考博文如下:
MAPPO:The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games
github代码:
MAPPO官方代码链接:https://github.com/marlbenchmark/on-policy
轻量版MAPPO,易移植:https://github.com/tinyzqh/light_mappo
MAPPO算法,是强化学习单智能体算法PPO在多智能体领域的改进。
此算法暂时先参考别人的博文,等我实际运用过,有了更深的理解之后,再来完善本内容。