Fix dim of action in q_learning tutorial (pytorch#114)

Author: quanvuong

intermediate_source/reinforcement_q_learning.py

@@ -332,7 +332,7 @@ def select_action(state):
     steps_done += 1
     if sample > eps_threshold:
         return model(
-            Variable(state, volatile=True).type(FloatTensor)).data.max(1)[1]
+            Variable(state, volatile=True).type(FloatTensor)).data.max(1)[1].view(1, 1)
     else:
         return LongTensor([[random.randrange(2)]])