Deflated Q-value iteration admits a projected switching-system model whose joint spectral radius can be strictly smaller than the discount factor, yielding a sharper convergence characterization while leaving the greedy policy sequence unchanged.
Puterman.Markov decision processes: Discrete stochastic dynamic programming
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Q-learning convergence rates can be characterized exactly through the joint spectral radius of a stochastic switching linear system representation of the error dynamics.
citing papers explorer
-
Switching-Geometry Analysis of Deflated Q-Value Iteration
Deflated Q-value iteration admits a projected switching-system model whose joint spectral radius can be strictly smaller than the discount factor, yielding a sharper convergence characterization while leaving the greedy policy sequence unchanged.