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

mqmix hypernet b2 #17

Open zcyyyyyyyyyyy opened 8 months ago

zcyyyyyyyyyyy commented 8 months ago

in mqmix mixer

self.hyperb2 = nn.Sequential( init(nn.Linear(self.cent_obs_dim, self.hypernet_hiddendim)), nn.ReLU(), init(nn.Linear(self.hypernet_hidden_dim, 1)) ).to(self.device)

should be

self.hyperb2 = nn.Sequential( init(nn.Linear(self.cent_obs_dim, self.mixer_hiddendim)), nn.ReLU(), init(nn.Linear(self.mixer_hidden_dim, 1)) ).to(self.device)

?