English

A constrained optimization perspective on actor critic algorithms and application to network routing

Machine Learning 2015-07-30 v1 Optimization and Control

Abstract

We propose a novel actor-critic algorithm with guaranteed convergence to an optimal policy for a discounted reward Markov decision process. The actor incorporates a descent direction that is motivated by the solution of a certain non-linear optimization problem. We also discuss an extension to incorporate function approximation and demonstrate the practicality of our algorithms on a network routing application.

Keywords

Cite

@article{arxiv.1507.07984,
  title  = {A constrained optimization perspective on actor critic algorithms and application to network routing},
  author = {Prashanth L. A. and H. L. Prasad and Shalabh Bhatnagar and Prakash Chandra},
  journal= {arXiv preprint arXiv:1507.07984},
  year   = {2015}
}
R2 v1 2026-06-22T10:21:07.544Z