rl model inf fix

core/orchestrator.py

@@ -540,7 +540,6 @@ class TradingOrchestrator:
         self._initialize_decision_fusion()  # Initialize fusion system
         self._initialize_transformer_model()  # Initialize transformer model
         self._initialize_enhanced_training_system()  # Initialize real-time training
-
     def _initialize_ml_models(self):
         """Initialize ML models for enhanced trading"""
         try:
@@ -1313,7 +1312,6 @@ class TradingOrchestrator:
 
         except Exception as e:
             logger.error(f"❌ Error clearing orchestrator session data: {e}")
-
     def sync_model_states_with_dashboard(self):
         """Sync model states with current dashboard values"""
         # Update based on the dashboard stats provided
@@ -2096,7 +2094,6 @@ class TradingOrchestrator:
             f"Decision callback registered: {callback.__name__ if hasattr(callback, '__name__') else 'unnamed'}"
         )
         return True
-
     async def make_trading_decision(self, symbol: str) -> Optional[TradingDecision]:
         """
         Make a trading decision for a symbol by combining all registered model outputs
@@ -3564,7 +3561,6 @@ class TradingOrchestrator:
                         
         except Exception as e:
             logger.error(f"Error in CNN long-term training: {e}")
-
     async def _evaluate_and_train_on_record(self, record: Dict, current_price: float):
         """Evaluate prediction outcome and train model"""
         try:
@@ -4487,7 +4483,7 @@ class TradingOrchestrator:
     async def _train_rl_model(
         self, model, model_name: str, model_input, prediction: Dict, reward: float
     ) -> bool:
-        """Train RL model (DQN) with experience replay"""
+        memory_size = 0  # Ensure memory_size is always defined
         try:
             # Convert prediction action to action index
             action_names = ["SELL", "HOLD", "BUY"]
@@ -7147,7 +7143,6 @@ class TradingOrchestrator:
         except Exception as e:
             logger.error(f"Error stopping enhanced training: {e}")
             return False
-
     def get_enhanced_training_stats(self) -> Dict[str, Any]:
         """Get enhanced training system statistics with orchestrator integration"""
         try:
@@ -8522,7 +8517,6 @@ class TradingOrchestrator:
                     status[data_type][symbol] = len(queue)
 
         return status
-
     def get_detailed_queue_status(self) -> Dict[str, Any]:
         """Get detailed status of all data queues with timestamps and data info"""
         detailed_status = {}
@@ -9078,7 +9072,6 @@ class TradingOrchestrator:
         except Exception as e:
             logger.error(f"Error populating initial queue data: {e}")
 
-    def _try_fallback_data_strategy(
         self, symbol: str, missing_data: List[Tuple[str, int, int]]
     ) -> bool:
         """
@@ -9178,4 +9171,4 @@ class TradingOrchestrator:
 
         except Exception as e:
             logger.error(f"Error in fallback data strategy: {e}")
-            return False
+            return False