rudhratej09 commited on
Commit
da66bbf
·
unverified ·
1 Parent(s): 86338e0
Files changed (1) hide show
  1. inference.py +3 -3
inference.py CHANGED
@@ -132,15 +132,15 @@ def log_step(step: int, action: str, reward: float, done: bool, error: Optional[
132
  )
133
 
134
 
135
- def log_end(success: bool, steps: int, rewards: List[float]) -> None:
136
  """
137
  Emit [END] line per OpenEnv spec.
138
- Format: [END] success=<true|false> steps=<n> rewards=<r1,r2,...,rn>
139
  """
140
  rewards_str = ",".join(f"{r:.2f}" for r in rewards)
141
  print(
142
  f"[END] success={str(success).lower()} steps={steps} "
143
- f"rewards={rewards_str}",
144
  flush=True,
145
  )
146
 
 
132
  )
133
 
134
 
135
+ def log_end(success: bool, steps: int, score: float, rewards: List[float]) -> None:
136
  """
137
  Emit [END] line per OpenEnv spec.
138
+ Format: [END] success=<true|false> steps=<n> score=<score> rewards=<r1,r2,...,rn>
139
  """
140
  rewards_str = ",".join(f"{r:.2f}" for r in rewards)
141
  print(
142
  f"[END] success={str(success).lower()} steps={steps} "
143
+ f"score={score:.2f} rewards={rewards_str}",
144
  flush=True,
145
  )
146