The Value of Observation for Monitoring Dynamic Systems
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 2474-2478.
Abstract
We consider the fundamental problem of monitoring (i.e. tracking) the belief state in a dynamic system, when the model is only approximately correct and when the initial belief state might be unknown. In this general setting where the model is (perhaps only slightly) mis-specified, monitoring (and consequently planning) may be impossible as errors might accumulate over time. We provide a new characterization, the emph{value of observation}, which allows us to bound the error accumulation. The value of observation is a parameter that governs how much information the observation provides. For instance, in Partially Observable MDPs when it is 1 the POMDP is an MDP while for an unobservable Markov Decision Process the parameter is 0. Thus, the new parameter characterizes a spectrum from MDPs to unobservable MDPs depending on the amount of information conveyed in the observations.
@inproceedings{ijcai2007p398,
title = {The Value of Observation for Monitoring Dynamic Systems},
author = {Even-Dar, Eyal and Kakade, Sham M. and Mansour, Yishay},
booktitle = {Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence, {IJCAI-07}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ramon López de Mántaras},
pages = {2474--2478},
year = {2007},
url = {https://ijcai.org/proceedings/2007/398},
}
TY - CPAPER TI - The Value of Observation for Monitoring Dynamic Systems AU - Even-Dar, Eyal AU - Kakade, Sham M. AU - Mansour, Yishay T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 2474 EP - 2478 UR - https://ijcai.org/proceedings/2007/398 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
