AI RESEARCH
ZAPS-DA: Zero-Phase Action Policy Smoothing with Decoupled Actor for Continuous Control in Reinforcement Learning
arXiv CS.LG
•
ArXi:2605.30612v1 Announce Type: cross Continuous control policies trained with off-policy reinforcement learning frequently exhibit high-frequency action jitter, rendering direct deployment on physical actuators impractical. Post-hoc filtering attenuates jitter but