made changes to reset()

server/app.py

@@ -119,7 +119,7 @@ def reset(req: ResetRequest = ResetRequest()):
         obs = env.reset(task_id=req.task_id)
     except ValueError as e:
         raise HTTPException(status_code=400, detail=str(e))
-    return StepResponse(observation=obs, reward=0.0, done=False)
+    return StepResponse(observation=obs, reward=obs.reward, done=False)
 
 
 @app.post("/step", response_model=StepResponse)

server/environment.py

@@ -62,7 +62,7 @@ class DataCleaningEnvironment:
         self._last_score   = self._compute_score()
         self._total_errors = self._count_errors()
 
-        return self._build_obs(0.0, False, "Episode started. Begin cleaning.")
+        return self._build_obs(self._last_score, False, "Episode started. Begin cleaning.")
 
     def step(self, action: DataCleaningAction) -> DataCleaningObservation:
         if self._df is None: