Stationary-weighted FQE achieves finite-sample linear convergence to the projected Bellman fixed point without Bellman completeness by reweighting regressions to the target stationary norm.
Semiparametric double reinforcement learning with applications to long-term causal inference.arXiv preprint arXiv:2501.06926, 2025a
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fitted $Q$ Evaluation Without Bellman Completeness via Stationary Weighting
Stationary-weighted FQE achieves finite-sample linear convergence to the projected Bellman fixed point without Bellman completeness by reweighting regressions to the target stationary norm.