inference format fix

inference.py

@@ -66,15 +66,18 @@ def log_start(task: str, env: str, model: str) -> None:
 def log_step(
     step: int, action: str, reward: float, done: bool, error: Optional[str]
 ) -> None:
+    error_val = error if error else "null"
+    done_val = str(done).lower()
     print(
-        f"[STEP] step={step} action={action} reward={reward} done={done} error={error}",
+        f"[STEP] step={step} action={action} reward={reward:.2f} done={done_val} error={error_val}",
         flush=True,
     )
 
 
 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={success} steps={steps} score={score} rewards={rewards}",
+        f"[END] success={str(success).lower()} steps={steps} score={score:.3f} rewards={rewards_str}",
         flush=True,
     )