AI RESEARCH
Fitted Q Evaluation Without Bellman Completeness via Stationary Weighting
arXiv CS.LG
•
ArXi:2512.23805v2 Announce Type: replace-cross Fitted Q-evaluation (FQE) is a foundational method for off-policy evaluation in reinforcement learning, but existing theory typically relies on Bellman completeness of the function class, a condition often violated in practice. This reliance is due to a fundamental norm mismatch: the Bellman operator is gamma-contractive in the L^2 norm induced by the target policy's stationary distribution, whereas standard FQE fits Bellman regressions under the behavior distribution.