Slightly modify the code to avoid warning.

`UserWarning: indexing with dtype torch.uint8 is now deprecated, please use a dtype torch.bool instead.`

Author: yang-jin-hai

intermediate_source/reinforcement_q_learning.py

@@ -408,7 +408,7 @@ def optimize_model():
     # Compute a mask of non-final states and concatenate the batch elements
     # (a final state would've been the one after which simulation ended)
     non_final_mask = torch.tensor(tuple(map(lambda s: s is not None,
-                                          batch.next_state)), device=device, dtype=torch.uint8)
+                                          batch.next_state)), device=device, dtype=torch.bool)
     non_final_next_states = torch.cat([s for s in batch.next_state
                                                 if s is not None])
     state_batch = torch.cat(batch.state)