cleanup and reorgnization

NN/models/dqn_agent.py

@@ -110,6 +110,9 @@ class DQNAgent:
         # DQN hyperparameters
         self.gamma = 0.99  # Discount factor
         
+        # Initialize avg_reward for dashboard compatibility
+        self.avg_reward = 0.0  # Average reward tracking for dashboard
+        
         # Load best checkpoint if available
         if self.enable_checkpoints:
             self.load_best_checkpoint()
@@ -215,7 +218,6 @@ class DQNAgent:
         
         # Performance tracking
         self.losses = []
-        self.avg_reward = 0.0
         self.no_improvement_count = 0
         
         # Confidence tracking