search

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

MADDPG rewards are getting higher and higher #7

Closed ollehhello closed 2 years ago

ollehhello commented 2 years ago

Hello, I train MADDPG to get higher and higher rew image ards in the context of simple_spread?

mawuji88 commented 2 years ago

I encountered the same situation. Have you solved it？