sumitsk / marl_transfer

Code for paper 'Learning transferable cooperative behaviors in multi-agent teams' (ICML 2019)
https://graphreason.github.io/papers/29.pdf
MIT License
108 stars 31 forks source link

Typo #4

Closed Ankur-Deka closed 4 years ago

Ankur-Deka commented 4 years ago

Line 47 in mpnn.py should probably be: self.policy_head = nn.Sequential(nn.Linear(self.h_dim, num_actions)... instead of: self.policy_head = nn.Sequential(nn.Linear(self.h_dim, self.h_dim)...

Ankur-Deka commented 4 years ago

I realized it's not a mistake