# FERPO: Entropy-Regularized Policy Optimization Without Critic Action Gradients

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/smmywh37l9hztkjzcv8bf77a0
- Original: https://arxiv.org/abs/2610.02198

## Summary

FERPO (Forward Entropy-Regularized Policy Optimization) is an online maximum-entropy reinforcement learning algorithm that improves the policy by differentiating the critic's value rather than its actions, avoiding policy-update problems caused when value predictions are accurate but action derivatives are unreliable.