1
A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak--Ruppert Averaging
无需投影的线性TD(0)用单一固定步长即可同时获得稳健与快速收敛,理论突破值得关注。
arXiv:2606.24981v1 Announce Type: new Abstract: We study linear TD(0) under Markovian sampling, where data are generated along a single trajectory. We…