Lakshminarayanan, Chandrashekar ; Bhatnagar, Shalabh (2017) A stability criterion for two timescale stochastic approximation schemes Automatica, 79 . pp. 108-114. ISSN 0005-1098
Full text not available from this repository.
Official URL: http://doi.org/10.1016/j.automatica.2016.12.014
Related URL: http://dx.doi.org/10.1016/j.automatica.2016.12.014
Abstract
We present the first sufficient conditions that guarantee stability of two-timescale stochastic approximation schemes. Our analysis is based on the ordinary differential equation (ODE) method and is an extension of the results in Borkar and Meyn (2000) for single-timescale schemes. As an application of our result, we show the stability of iterates in a two-timescale stochastic approximation scheme arising in reinforcement learning.
| Item Type: | Article |
|---|---|
| Source: | Copyright of this article belongs to Elsevier B.V. |
| ID Code: | 116466 |
| Deposited On: | 12 Apr 2021 05:58 |
| Last Modified: | 12 Apr 2021 05:58 |
Repository Staff Only: item control page
