diff sac_motif_freed_pe.py
@@ -601,7 +601,6 @@ class sac:
         # Finally, update target networks by polyak averaging.
 
         with torch.no_grad():
-            self.ac_targ.load_state_dict(self.ac.state_dict())
             for p, p_targ in zip(self.ac.parameters(), self.ac_targ.parameters()):
                 # NB: We use an in-place operations "mul_", "add_" to update target
                 # params, as opposed to "mul" and "add", which would make new tensors.
