pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Ratio-Variance Regularized Policy Optimization

cs.LG · 2026-05-26 · unverdicted · novelty 5.0

R²VPO uses ratio-variance regularization as a distributional soft brake on policy updates, claiming better performance than PPO on math reasoning and robotic control without hard clipping.

citing papers explorer

Showing 1 of 1 citing paper.

  • Ratio-Variance Regularized Policy Optimization cs.LG · 2026-05-26 · unverdicted · none · ref 24

    R²VPO uses ratio-variance regularization as a distributional soft brake on policy updates, claiming better performance than PPO on math reasoning and robotic control without hard clipping.