guest ::
| Home > Conference materials > Papers > On Approximate Fully Probabilistic Design of Decision-Making Units |
Original title:
On Approximate Fully Probabilistic Design of Decision-Making Units
Authors: Kárný, Miroslav
Document type: Papers
Conference/Event: The 3rd International Workshop on Scalable Decision Making: Uncertainty, Imperfection, Deliberation held in conjunction with ECML/PKDD 2013, Prague (CZ), 2013-09-23 / 2013-09-23
Year: 2013
Language: eng
Abstract: An efficient support of a single decision maker is vital in constructing scalable systems addressing complex decision-making (DM) tasks. Fully probabilistic design (FPD) of DM strategies, an extension of dynamic Bayesian DM, provides a firm basis for such a support. The limited cognitive and evaluation resources of the supported decision maker cause that theoretically optimal solutions are realised only approximately. Thus, the truly efficient support has to include reliable means for constructing approximate solutions of DM subtasks. The current paper deals with the design of the approximately optimal DM strategy for a known environment model and adequately described DM preferences. The design relies on: a) the explicit minimiser found within FPD; b) randomised nature of the strategy provided by FPD.
Keywords: Bayesian learning; decision making; fully probabilistic design of DM strategies; linear-quadratic DM; minimum cross-entropy principle
Project no.: GA13-13502S (CEP)
Funding provider: GA ČR
Host item entry: Preprints of the 3rd International Workshop on Scalable Decision Making held in conjunction with ECML/PKDD 2013, ISBN 978-80-903834-8-7
Institution: Institute of Information Theory and Automation AS ČR (web)
Document availability information: Fulltext is available at external website.
External URL: http://library.utia.cas.cz/separaty/2013/AS/karny-on approximate fully probabilistic design of decision-making units.pdf
Original record: http://hdl.handle.net/11104/0224702
Permalink: http://www.nusl.cz/ntk/nusl-156644
The record appears in these collections:
Research > Institutes ASCR > Institute of Information Theory and Automation
Conference materials > Papers
Authors: Kárný, Miroslav
Document type: Papers
Conference/Event: The 3rd International Workshop on Scalable Decision Making: Uncertainty, Imperfection, Deliberation held in conjunction with ECML/PKDD 2013, Prague (CZ), 2013-09-23 / 2013-09-23
Year: 2013
Language: eng
Abstract: An efficient support of a single decision maker is vital in constructing scalable systems addressing complex decision-making (DM) tasks. Fully probabilistic design (FPD) of DM strategies, an extension of dynamic Bayesian DM, provides a firm basis for such a support. The limited cognitive and evaluation resources of the supported decision maker cause that theoretically optimal solutions are realised only approximately. Thus, the truly efficient support has to include reliable means for constructing approximate solutions of DM subtasks. The current paper deals with the design of the approximately optimal DM strategy for a known environment model and adequately described DM preferences. The design relies on: a) the explicit minimiser found within FPD; b) randomised nature of the strategy provided by FPD.
Keywords: Bayesian learning; decision making; fully probabilistic design of DM strategies; linear-quadratic DM; minimum cross-entropy principle
Project no.: GA13-13502S (CEP)
Funding provider: GA ČR
Host item entry: Preprints of the 3rd International Workshop on Scalable Decision Making held in conjunction with ECML/PKDD 2013, ISBN 978-80-903834-8-7
Institution: Institute of Information Theory and Automation AS ČR (web)
Document availability information: Fulltext is available at external website.
External URL: http://library.utia.cas.cz/separaty/2013/AS/karny-on approximate fully probabilistic design of decision-making units.pdf
Original record: http://hdl.handle.net/11104/0224702
Permalink: http://www.nusl.cz/ntk/nusl-156644
The record appears in these collections:
Research > Institutes ASCR > Institute of Information Theory and Automation
Conference materials > Papers
Record created 2013-10-10, last modified 2021-11-24