Lakshminarayanan, Chandrashekar ; Bhatnagar, Shalabh ; Szepesvari, Csaba (2018) A Linearly Relaxed Approximate Linear Program for Markov Decision Processes IEEE Transactions on Automatic Control, 63 (4). pp. 1185-1191. ISSN 0018-9286
Full text not available from this repository.
Official URL: http://doi.org/10.1109/TAC.2017.2743163
Related URL: http://dx.doi.org/10.1109/TAC.2017.2743163
Abstract
Approximate linear programming (ALP) and its variants have been widely applied to Markov decision processes (MDPs) with a large number of states. A serious limitation of ALP is that it has an intractable number of constraints, as a result of which constraint approximations are of interest. In this paper, we define a linearly relaxed approximation linear program (LRALP) that has a tractable number of constraints, obtained as positive linear combinations of the original constraints of the ALP. The main contribution is a novel performance bound for LRALP.
| Item Type: | Article |
|---|---|
| Source: | Copyright of this article belongs to Institute of Electrical and Electronics Engineers. |
| Keywords: | Approximate Linear Programming (ALP) , Markov Decision Processes (MDPS). |
| ID Code: | 116459 |
| Deposited On: | 12 Apr 2021 05:56 |
| Last Modified: | 12 Apr 2021 05:56 |
Repository Staff Only: item control page
