Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10413114 | Systems & Control Letters | 2005 | 7 Pages |
Abstract
An actor-critic type reinforcement learning algorithm is proposed and analyzed for constrained controlled Markov decision processes. The analysis uses multiscale stochastic approximation theory and the `envelope theorem' of mathematical economics.
Related Topics
Physical Sciences and Engineering
Engineering
Control and Systems Engineering
Authors
V.S. Borkar,