fix: reset reward 0.01 not 0.0

server/app.py

@@ -49,7 +49,7 @@ class ResetSchemaFixMiddleware(BaseHTTPMiddleware):
                         fixed_data = {
                             "observation": data["observation"],
                             "done": data.get("done", False),
-                            "reward": 0.0,
+                            "reward": 0.01,
                             "metadata": data.get("metadata", {}),
                             "info": {}
                         }
@@ -113,7 +113,7 @@ async def reset_env(request: Request):
         fixed_response = {
             "observation": observation.model_dump(),
             "done": False,
-            "reward": 0.0,
+            "reward": 0.01,
             "metadata": {},
             "info": {}
         }