improve training and model data

config.yaml

@@ -197,6 +197,7 @@ enhanced_training:
   enabled: true                    # Enable enhanced real-time training
   auto_start: true                 # Automatically start training when orchestrator starts
   training_intervals:
+    cob_rl_training_interval: 1    # Train COB RL every 1 second (HIGHEST PRIORITY)
     dqn_training_interval: 5       # Train DQN every 5 seconds
     cnn_training_interval: 10      # Train CNN every 10 seconds
     validation_interval: 60        # Validate every minute
@@ -206,6 +207,11 @@ enhanced_training:
   adaptation_threshold: 0.1        # Performance threshold for adaptation
   forward_looking_predictions: true # Enable forward-looking prediction validation
   
+  # COB RL Priority Settings (since order book imbalance predicts price moves)
+  cob_rl_priority: true            # Enable COB RL as highest priority model
+  cob_rl_batch_size: 16           # Smaller batches for faster COB updates
+  cob_rl_min_samples: 5           # Lower threshold for COB training
+  
 # Real-time RL COB Trader Configuration
 realtime_rl:
   # Model parameters for 400M parameter network (faster startup)