AI RESEARCH
Switching-Geometry Analysis of Deflated Q-Value Iteration
arXiv CS.AI
•
ArXi:2605.10811v1 Announce Type: cross This paper develops a joint spectral radius (JSR) framework for analyzing rank-one deflated Q-value iteration (Q-VI) in discounted Marko decision process control. Focusing on an all-ones residual correction, we interpret the resulting algorithm through the geometry of switching systems and, to the best of our knowledge, give the first JSR-based convergence analysis of deflated Q-VI for policy optimization problems.