Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics 事件

Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics arXiv:2606.02645v1 Announce Type: cross Abstract: Periodic target updates in Q-learning and soft target updates in actor-critic methods are empirically well established stabilization mechanisms, but their precise theoretical explanation is still incomplete. This paper gives a rigorous and exact analysis of these mechanisms for Q-learning with linear function approximation (linear Q-learning) using the exact switched line