Update symphony_S2/train.py

symphony_S2/train.py

@@ -193,9 +193,9 @@ def sim_loop(env, episodes, testing, Q_learning, algo, total_rewards, total_step
                 save(algo, total_rewards, total_steps)
                 print("start testing")
                 log_file.write(str(total_steps) + ",")
-                Return = sim_loop(env_test, 25, True, Q_learning, algo, [], total_steps=0)
+                test_return = sim_loop(env_test, 25, True, Q_learning, algo, [], total_steps=0)
                 print("end of testing")
-                log_file.write(str(round(Return, 2)) + "\n")
+                log_file.write(str(round(test_return, 2)) + "\n")
 
 
             # if steps is close to episode limit (e.g. 950) we shut down actions and leave noise to get Terminal Transition:
@@ -230,4 +230,4 @@ Q_learning, total_rewards, total_steps = load(algo, Q_learning)
 if not Q_learning: log_file.clean()
 
 # Training
-sim_loop(env, num_episodes, False, Q_learning, algo, total_rewards, total_steps)
+sim_loop(env, num_episodes, False, Q_learning, algo, total_rewards, total_steps)