search

xuehy / pytorch-maddpg

A pytorch implementation of MADDPG (multi-agent deep deterministic policy gradient)
605 stars 122 forks source link

squeeze problem #12

Closed Ayeliauk closed 5 years ago

Ayeliauk commented 5 years ago

thank you for your codes Traceback (most recent call last): File "maina.py", line 76, in c_loss, a_loss = maddpg.update_policy() File "/content/drive/drive/matd3/MADDPG.py", line 117, in update_policy self.n_agents * self.n_actions) AttributeError: 'tuple' object has no attribute 'squeeze'

Ayeliauk commented 5 years ago

if I put squeeze infront，then it occour： RuntimeError: shape mismatch: value tensor of shape [999, 1] cannot be broadcast to indexing result of shape [999]