Article

FERPO: Entropy-Regularized Policy Optimization Without Critic Action Gradients

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.

Part of the event: FERPO: An Entropy-Regularized Policy Optimization Algorithm Without Relying on Critic Action Gradients

This page provides a summary and source link only.