update type of evaluate_actions to list tensor (#4747)

ml-agents/mlagents/trainers/policy/torch_policy.py

 
     def evaluate_actions(
         self,
-        vec_obs: torch.Tensor,
-        vis_obs: torch.Tensor,
+        vec_obs: List[torch.Tensor],
+        vis_obs: List[torch.Tensor],
         actions: AgentAction,
         masks: Optional[torch.Tensor] = None,
         memories: Optional[torch.Tensor] = None,