fix: update log_end score formatting to .3f to strictly match sample script implementation

inference.py

@@ -115,7 +115,7 @@ 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} score={score:.2f} rewards={rewards_str}",
+        f"[END] success={str(success).lower()} steps={steps} score={score:.3f} rewards={rewards_str}",
         flush=True,
     )