Towards Fully Probabilistic Cooperative Decision Making

0501237 - ÚTIA 2020 RIV CH eng C - Conference Paper (international conference)
Kárný, Miroslav - Alizadeh, Zohreh
Towards Fully Probabilistic Cooperative Decision Making.
Multi-Agent Systems : 16th European Conference, EUMAS 2018, Revised Selected Papers. Cham: Springer, 2019 - (Slavkovik, M.), č. článku 11. Lecture Notes in Artificial Intelligence, 11450. ISBN 978-3-030-14173-8.
[Eumas 2018. Bergen (NO), 06.12.2018-07.12.2018]
R&D Projects: GA ČR GA16-09848S
Institutional support: RVO:67985556
Keywords : Decision making * Cooperation * Fully probabilistic design * Bayesian learning
OECD category: Statistics and probability
http://library.utia.cas.cz/separaty/2019/AS/karny-0501237.pdf

Modern prescriptive decision theories try to support the dynamic decision making (DM) in incompletely-known, stochastic, and complex environments. Distributed solutions single out as the only universal and scalable way to cope with DM complexity and with limited DM resources. They require a solid cooperation scheme, which har- AQ1 monises disparate aims and abilities of involved agents (human decision makers, DM realising devices and their mixed groups). The paper outlines a distributed fully probabilistic DM. Its flat structuring enables a fully-scalable cooperative DM of adaptive and wise selfish agents. The paper elaborates the cooperation based on sharing and processing agents’ aims in the way, which negligibly increases agents’ deliberation effort, while preserving advantages of distributed DM. Simulation results indicate the strength of the approach and confirm the possibility of using an agent-specific feedback for controlling its cooperation.
Permanent Link: http://hdl.handle.net/11104/0293458