changed

inference.py

@@ -40,7 +40,7 @@ def log_step(step: int, action: str, reward: float, done: bool, error: Optional[
 
 def log_end(success: bool, steps: int, score: float, rewards: List[float]) -> None:
     rewards_str = ",".join(f"{r:.2f}" for r in rewards)
-    print(f"[END] success={str(success).lower()} steps={steps} rewards={rewards_str}", flush=True)
+    print(f"[END] success={str(success).lower()} steps={steps} score={score:.3f} rewards={rewards_str}", flush=True)
 
 
 # ─────────────────────────────────────────────