Lizhi-sjtu/MARL-code-pytorch
Concise pytorch implements of MARL algorithms, including MAPPO, MADDPG, MATD3, QMIX and VDN.
PythonMIT
Issues
- 4
import make_env from make_env怎么改
#20 opened by sjn123hhh - 1
maddpg在mpe:simple_spread中不收敛
#21 opened by cecilia116 - 0
请问大佬现在还在从事多智能体相关工作么?这两年有产出代表性论文么?这块除了游戏还有其它应用么?
#23 opened by ymzx - 5
Discrete action
#3 opened by Bruce-Lan-ZY - 0
An error occurred after the environment name was changed to simple_adversary
#22 opened by restlessfish - 1
tensorboard==0.6.0
#2 opened by Xiyou521 - 1
MAPPO如何Decentrolised Execute
#18 opened by ErwinLiYH - 2
mappo测试和训练差异较大
#10 opened by dutlzn - 0
请问mappo如何改为连续动作?
#19 opened by Lxsogo - 0
关于MAPPO的episode
#17 opened by hj5717 - 0
- 0
是否支持使用自创环境?
#15 opened by DurableFrank - 0
the way to update actor and critic is quite different from the orignal mappo, i wonder this difference have benen tested yet
#14 opened by LuErShuai - 0
MATD3
#13 opened by zhaojintang - 0
MATD3 on SMAC
#12 opened by SEU-cjy - 4
Anyone knows how to run trained models?
#6 opened by lukaskocian - 0
关于MADDPG的critic
#8 opened by Yuxin916 - 0
- 0
IndexError: invalid index to scalar variable.
#5 opened by skonwa - 0
Continuous Action
#9 opened by zhl606 - 0
代码是否支持对死亡智能体的处理呢?
#7 opened by dutlzn - 0
MAPPO 'Box' object has no attribute 'n'
#4 opened by sling0318 - 2
关于MAPPO中Gradient clip 参数设置的问题
#1 opened by shelby-ce