Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 DetailsÜbersicht
  Balancing Safety and Exploitability in Opponent Modeling

Wang, Z., Boularias, A., Mülling, K., & Peters, J. (2011). Balancing Safety and Exploitability in Opponent Modeling. In Twenty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2011) (pp. 1515-1520). Menlo Park, CA, USA: AAAI Press.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-BAD0-D Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-BAD1-B
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Wang, Z1, Autor           
Boularias, A1, Autor           
Mülling, K1, Autor           
Peters, J1, 2, Autor           
Burgard D. Roth, W., Herausgeber
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Opponent modeling is a critical mechanism in repeated games. It allows a player to adapt its strategy in order to better respond to the presumed preferences of his opponents. We introduce a new modeling technique that adaptively balances exploitability and risk reduction. An opponent’s strategy is modeled with a set of possible strategies that contain the actual strategy with a high probability. The algorithm is safe as the expected payoff is above the minimax payoff with a high probability, and can exploit the opponents’ preferences when sufficient observations have been obtained. We apply them to normal-form games and stochastic games with a finite number of stages. The performance of the proposed approach is first demonstrated on repeated rock-paper-scissors games. Subsequently, the approach is evaluated in a human-robot table-tennis setting where the robot player learns to prepare to return a served ball. By modeling the human players, the robot chooses a forehand, backhand or middle preparation pose before they serve. The learned strategies can exploit the opponent’s preferences, leading to a higher rate of successful returns.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2011-08
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: ISBN: 978-1-577-35507-6
URI: http://www.aaai.org/Conferences/AAAI/aaai11.php
BibTex Citekey: WangBMP2011
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Twenty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2011)
Veranstaltungsort: San Francisco, CA, USA
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Twenty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2011)
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Menlo Park, CA, USA : AAAI Press
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1515 - 1520 Identifikator: -