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.
Auro: Reinforcement learning for adaptive user retention optimization in recommender systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.