The code for paper 《基于自注意力机制和策略映射重组的多智能体强化学习算法》summbitted to 《计算机学报》. Using <Python main.py --env_id "" --model_name ""> to start. The requirement.txt will come soon.
githuuuuub/PolicyMappingTransformerMARL
The code for paper 《基于自注意力机制和策略映射重组的多智能体强化学习算法》summbitted to 《计算机学报》
Python