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.
By the local contraction bound (applied atQ (k)), ek+1 ≤ γ+β loc eα k ek, so the per-iteration modulus ρk := ek+1 ek satisfies ρk −γ≤β loc eα k
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
-
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.