add first example with OpenRLHF

reasoning_gym/dataset.py

@@ -49,3 +49,17 @@ class ProceduralDataset(ABC, Sized, Iterable[Dict[str, Any]]):
                 - metadata: dict
         """
         raise NotImplementedError
+
+    def score_answer(self, answer: Optional[str], entry: Dict[str, any]) -> float:
+        """Overwrite this method in derived classes if a single oracle answer is not available."""
+        oracle_answer = entry["answer"]
+        reward = 0
+        if answer is not None:
+            if answer == oracle_answer:
+                reward = 1.0
+            elif oracle_answer in answer:
+                reward = 0.5
+            else:
+                reward = 0.01
+
+        return reward