Finite-sample risk bounds for DQN with ReLU networks are extended to τ-mixing data, showing an extra dimensionality penalty in the convergence rate due to dependence.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A consistent two-stage GPH-filtered Hannan-Rissanen generalized information criterion for selecting finite AR and MA orders in ARFIMA models with growing candidate sets.
citing papers explorer
-
Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $\tau$-Mixing
Finite-sample risk bounds for DQN with ReLU networks are extended to τ-mixing data, showing an extra dimensionality penalty in the convergence rate due to dependence.
-
A GPH-Filtered Hannan--Rissanen Information Criterion for ARFIMA Order Selection
A consistent two-stage GPH-filtered Hannan-Rissanen generalized information criterion for selecting finite AR and MA orders in ARFIMA models with growing candidate sets.