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.
A variant of the wang-foster-kakade lower bound for the discounted setting
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2025 4representative citing papers
Bellman calibration supplies a new reliability criterion and post-hoc recalibration method for value functions in offline RL, with finite-sample guarantees at one-dimensional nonparametric rates that avoid Bellman completeness and realizability assumptions.
GenPQR recovers normalized rewards in maximum-entropy IRL by estimating the policy with classification and the soft Q-function with regression, providing modular finite-sample guarantees under general function approximation.
Stationary reweighting of soft fitted Q-iteration yields finite-sample local linear convergence to the projected fixed point under approximate realizability and controlled weighting error, even without Bellman completeness.
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.
-
Bellman Calibration for $V$-Learning in Offline Reinforcement Learning
Bellman calibration supplies a new reliability criterion and post-hoc recalibration method for value functions in offline RL, with finite-sample guarantees at one-dimensional nonparametric rates that avoid Bellman completeness and realizability assumptions.
-
Inverse Reinforcement Learning with Just Classification and a Few Regressions
GenPQR recovers normalized rewards in maximum-entropy IRL by estimating the policy with classification and the soft Q-function with regression, providing modular finite-sample guarantees under general function approximation.
-
Stationary Reweighting Yields Local Convergence of Soft Fitted Q-Iteration
Stationary reweighting of soft fitted Q-iteration yields finite-sample local linear convergence to the projected fixed point under approximate realizability and controlled weighting error, even without Bellman completeness.