Update app.py

app.py

@@ -120,7 +120,7 @@ async def predict(request: TransactionRequest):
         if request.use_rl:
             ppo = load_ppo_model()
             obs = pad[0]
-            action, _ = ppo.predict(obs)
+            action, _ = ppo.predict(obs, deterministic=True)  # Force deterministic
             print(f"RL Action: {action}, Observation: {obs}")
             cat_idx = action // num_subcategories
             subcat_idx = action % num_subcategories