Ensure that PC does at least one comparison per iteration.

HumanCompatibleAI · Jan 11, 2024 · 55aa6eb · 55aa6eb
1 parent d7a7da8
commit 55aa6eb
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/src/imitation/algorithms/preference_comparisons.py b/src/imitation/algorithms/preference_comparisons.py
@@ -1678,6 +1678,8 @@ def train(
         unnormalized_probs = vec_schedule(np.linspace(0, 1, self.num_iterations))
         probs = unnormalized_probs / np.sum(unnormalized_probs)
         shares = util.oric(probs * total_comparisons)
+        shares[shares <= 0] = 1  # ensure we at least request one comparison per iteration
+
         schedule = [initial_comparisons] + shares.tolist()
         print(f"Query schedule: {schedule}")