This paper presents the Deniz agent that has been specifically designed to support human negotiators in their bidding. The design of Deniz is done with the criteria of robustness and the availability of small data, due to a small number of negotiation rounds in mind. Deniz’s bidding strategy is based on an existing optimal concession strategy that concedes in relation to the expected duration of the negotiation. This accounts for the small data and small number of rounds. Deniz deploys an adaptive behavior-based mechanism to make it robust against exploitation. We tested Deniz against typical bidding strategies and against human negotiators. Our evaluation shows that Deniz is robust against exploitation and gains statistically significant higher utilities than human test subjects, even though it is not designed specifically to get the highest utility against humans.
|Title of host publication||Advances in Automated Negotiations, ACAN 2018|
|Editors||Takayuki Ito, Minjie Zhang, Reyhan Aydogan|
|Number of pages||16|
|Publication status||Published - 2021|
|Event||11th International Workshop on Automated Negotiation, ACAN 2018 - Stockholm, Sweden|
Duration: 13 Jul 2018 → 19 Jul 2018
|Name||Studies in Computational Intelligence|
|Conference||11th International Workshop on Automated Negotiation, ACAN 2018|
|Period||13/07/18 → 19/07/18|
Bibliographical noteGreen Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.