We study convex Constrained Markov Decision Processes (CMDPs) in which the objective is concave and constraints are state-action occupancy measure. propose a policy-based primal-dual algorithm that updates primal variable via policy gradient ascent dual projected sub-gradient descent. Despite loss of additivity structure nonconvex nature, we establish global convergence proposed by leveraging h...

In this article, we study the problem of minimizing sum potentially nondifferentiable convex cost functions with partially overlapping dependences in an asynchronous manner, where communication network is not coordinated. We behavior algorithm based on dual decomposition and block coordinate subgradient methods under assumptions weaker than those used literature. At same time, allow different a...

Primal–dual hybrid gradient (PDHG) and alternating direction method of multipliers (ADMM) are popular first-order optimization methods. They easy to implement have diverse applications. As methods, however, they sensitive problem conditions can struggle reach the desired accuracy. To improve their performance, researchers proposed techniques such as diagonal preconditioning inexact subproblems....