Showing 2026Show all
3 papers · 1 filter
math.OC2026
Does Policy Mirror Descent Converge in Policy with Non-Decomposable Mirror Maps? A Counterexample
Wenye Li, Ke Wei
Policy mirror descent (PMD) refers to a class of policy optimization methods associated with different mirror maps. For a broad class of decomposable Legendre mirror maps encompass…
cs.LG2026
Fast Regularized Policy Mirror Descent with One-Step TD Updates
Qipei Chen, Wenye Li, Yule Sun +1
Policy mirror descent (PMD) enjoys fast convergence in regularized Markov decision processes (MDPs), but existing guarantees often rely on exact or increasingly accurate policy eva…
math.OC2026
On the Policy Convergence of Policy Mirror Descent Methods
Wenye Li, Ke Wei
We study the policy convergence of unregularized policy mirror descent (PMD) with arbitrary constant step sizes for finite discounted Markov decision processes. We focus on decompo…