Rethinking Policy Gradients: Score Centering Skips Importance Sampling Entirely

brandondamos · x · 2026-09-22

Yifei Wang highlights a discussion by YouJiacheng on rethinking policy gradients: instead of optimizing Ep[R] with high-variance importance sampling, score centering optimizes Eq[R] — samples already come from q, so no IS is needed. Since q (inference engine/old policy) can't be optimized directly, p's gradient serves as a biased surrogate, which is exactly a STE. YouJiacheng shows this extends beyond linear policies: for gradients w.r.t. logits, the centered score equals ea - q, making score centering the estimator zp + sg(zq - zp). A perspective shift from optimizing the p-objective to the q-objective that yields major simplification.

Related event: Score Centering in Policy Gradients Revealed as a Straight-Through Estimator(3 posts)→

Original post →

More from Research

Research channel →