off-policy
off-policy copied to clipboard
mqmix hypernet b2
in mqmix mixer
self.hyper_b2 = nn.Sequential( init_(nn.Linear(self.cent_obs_dim, self.hypernet_hidden_dim)), nn.ReLU(), init_(nn.Linear(self.hypernet_hidden_dim, 1)) ).to(self.device)
should be
self.hyper_b2 = nn.Sequential( init_(nn.Linear(self.cent_obs_dim, self.mixer_hidden_dim)), nn.ReLU(), init_(nn.Linear(self.mixer_hidden_dim, 1)) ).to(self.device)
?