Vladislav Z. B. Tadic, Arnaud Doucet, Sumeetpal S. Singh. Two time-scale stochastic approximation for constrained stochastic optimization and constrained Markov decision problems. In American Control Conference, ACC 2003, Denver, CO, USA, June 4-6 2003. pages 4736-4741, IEEE, 2003. [doi]
Abstract is missing.