AI RESEARCH
On the Fundamental Limitations of Dual Static CVaR Decompositions in Markov Decision Processes
arXiv CS.LG
•
ArXi:2507.14005v2 Announce Type: replace It was recently shown that dynamic programming (DP) methods for finding static CVaR-optimal policies in Marko Decision Processes (MDPs) can fail when based on the dual formulation, yet the root cause of this failure remains unclear. We expand on these findings by shifting focus from policy optimization to the seemingly simpler task of policy evaluation. We show that evaluating the static CVaR of a given policy can be framed as two distinct minimization problems. We.