add back comment referring to issue 156

GFNOrg · Apr 2, 2024 · 368af4c · 368af4c
1 parent 8b2d124
commit 368af4c
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/src/gfn/gflownet/detailed_balance.py b/src/gfn/gflownet/detailed_balance.py
@@ -81,6 +81,9 @@ def get_scores(
             module_output = self.pf(
                 states
             )  # TODO: Inefficient duplication in case of tempered policy
+            # The Transitions container should then have some
+            # estimator_outputs attribute as well, to avoid duplication here ?
+            # See (#156).
             valid_log_pf_actions = self.pf.to_probability_distribution(
                 states, module_output
             ).log_prob(actions.tensor)