testing the merge

backend/agent.py

@@ -34,7 +34,7 @@ def q_learning(space, activities):
     mean_time = 0
 
     # Train the agent using Q-learning
-    num_episodes = 100
+    num_episodes = 10
     for episode in range(num_episodes):
         state, _ = env.reset()
         state = env.flatten_observation(state)