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.
Off-policy deep reinforcement learning without exploration
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ML 2years
2025 2representative 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.
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.