训练奖励越来越低？

marlbenchmark / off-policy

PyTorch implementations of popular off-policy multi-agent reinforcement learning algorithms, including QMix, VDN, MADDPG, and MATD3.

MIT License

386 stars 67 forks source link

Closed HorizonLiang closed 2 years ago

HorizonLiang commented 2 years ago

运行train_mpe.py文件，日志显示奖励越来越低。

ollehhello commented 2 years ago

你好，我也有相同的问题，请问是什么情况呢？

ollehhello commented 2 years ago

我运行的是MADDPG