search

starry-sky6688 / MARL-Algorithms

Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraft II
1.42k stars 279 forks source link

关于attention的训练依据的问题 #114

Closed honey-mxy closed 3 months ago

honey-mxy commented 3 months ago

作者您好！请问hard attention和softattention的训练依据是什么呢？好像没有找到对应的loss function，是和智能体强化学习共用目标吗？十分感谢！

starry-sky6688 commented 3 months ago

g2anet只是一个网络，它需要配合reinforce或者central-v来进行训练，以central-v为例，更新g2anet的loss函数在这里：

https://github.com/starry-sky6688/MARL-Algorithms/blob/e9e32e122f1b25e1139b82bebbb7ed81dc1e2320/policy/central_v.py#L100