Original title:
Sharing of knowledge and preferences among imperfect Bayesian decision makers
Authors:
Kárný, Miroslav ; Guy, Tatiana Valentine Document type: Papers Conference/Event: 24th Annual Conference on Neural Information Processing Systems, Whistler, B.C. Canada (CA), 2010-12-06 / 2010-12-11
Year:
2010
Language:
eng Abstract:
Bayesian decision theory provides a strong theoretical basis for a single-participant decision making under uncertainty, that can be extended to multi-participant problems. However Bayesian decision theory assumes unlimited abilities of a participant to probabilistically model participant´s environment and to optimise decision-making strategy. The paper proposes a methodology for sharing of knowledge and strategies among participants, that helps to overcome the non-realistic assumption on participant´s unlimited abilities.
Keywords:
Bayesian decision makers; knowledge sharing; preference sharing Project no.: CEZ:AV0Z10750506 (CEP), 1M0572 (CEP), GA102/08/0567 (CEP) Funding provider: GA MŠk, GA ČR Host item entry: Decision Making with Multiple Imperfect Decision Makers, ISBN 978-80-903834-5-6