Thumbnail Image
Publication

Multi-policy optimization in decentralized autonomic systems

Date
2009
Abstract
This paper addresses the challenge of multi-policy optimization in decentralized autonomic systems. We evaluate several multi-policy reinforcement learning-based optimization techniques in an urban tra c control simulation, a canonical example of a decentralized autonomic system. Our results indicate that W-learning, which learns separately for each policy and then selects between nominated actions based on current action importance, is a suitable approach for optimization towards multiple policies on non-collaborating agents in heterogeneous autonomic environments.
Supervisor
Description
peer-reviewed
Publisher
IFAAMAS
Citation
8th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2009);
Collections
Lero - The Science Foundation Ireland Research Centre for Software
Show all metadata
Files
Thumbnail Image
Dusparic%202009.pdf
Adobe PDF, 108.38 KB
Keywords
autonomic computing, reinforcement learning, decentralized systems
ULRR Identifiers
https://researchrepository.ul.ie/handle/10344/2364
 https://doi.org/10.34961/950
Funding code
Funding Information
Science Foundation Ireland (SFI)
Sustainable Development Goals
External Link
Type
Meetings and Proceedings
Rights
https://creativecommons.org/licenses/by-nc-sa/1.0/
License