A single stepsize for unprojected linear TD(0) under Markovian sampling yields simultaneous high-probability robust curvature-free and fast curvature-dependent rates via Polyak-Ruppert averaging.
arXiv preprint arXiv:2603.02577 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak--Ruppert Averaging
A single stepsize for unprojected linear TD(0) under Markovian sampling yields simultaneous high-probability robust curvature-free and fast curvature-dependent rates via Polyak-Ruppert averaging.