Exploration vs Exploitation with Partially Observable Gaussian Autoregressive Arms

Kuhn, Julia; Mandjes, Michel; Nazarathy, Yoni

Exploration vs Exploitation with Partially Observable Gaussian Autoregressive Arms

Kuhn, Julia and Mandjes, Michel and Nazarathy, Yoni (2015) Exploration vs Exploitation with Partially Observable Gaussian Autoregressive Arms. In: 8th International Conference on Performance Evaluation Methodologies and Tools.

PDF
21273.pdf
Download (444kB)

Abstract

We consider a restless bandit problem with Gaussian autoregressive arms, where the state of an arm is only observed when it is played and the state-dependent reward is collected. Since arms are only partially observable, a good decision policy needs to account for the fact that information about the

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Date Deposited:	04 Mar 2026 10:26
Last Modified:	17 Apr 2026 18:58
URI:	http://eprints.eai.eu/id/eprint/12720

Actions (login required)

: View Item