Borkar, Vivek S. (2021) A concentration bound for contractive stochastic approximation Systems & Control Letters, 153 . p. 104947. ISSN 0167-6911
Full text not available from this repository.
Official URL: http://doi.org/10.1016/j.sysconle.2021.104947
Related URL: http://dx.doi.org/10.1016/j.sysconle.2021.104947
Abstract
We derive a ‘high probability’ concentration bound for stochastic approximation schemes for finding the fixed point of a contraction map, and illustrate its applications in reinforcement learning for approximate dynamic programming.
| Item Type: | Article |
|---|---|
| Source: | Copyright of this article belongs to Elsevier Science. |
| ID Code: | 135135 |
| Deposited On: | 19 Jan 2023 07:58 |
| Last Modified: | 19 Jan 2023 07:58 |
Repository Staff Only: item control page
