[2F1-E-3] Agents: interaction and decision

[2F1-E-3-01] ANAC 2018: Repeated Multilateral Negotiation League

Reyhan Aydogan^1,4, 〇Katsuhide Fujita², Tim Baarslag³, Catholijn M. Jonker⁴, Takayuki Ito⁵ (1. Ozyegin University, 2. Tokyo University of Agriculture and Technology Tokyo, 3. Centrum Wiskunde & Informatica, 4. Delft University of Technology, 5. Nagoya Institute of Technology)

キーワード：Automated Negotiation, AI Competition, Repeated Multilateral Negotiation

There are a number of research challenges in the field of Automated Negotiation. The Ninth International Automated Negotiating Agent Competition aimed to encourage participants to develop effective negotiating agents, which can negotiate with multiple opponents more than once. This paper discusses essential research challenges for such negotiations as well as presenting the competition set-up and results. Results showed that winner agents mostly adopt hybrid bidding strategies and take their opponents' preferences as well as their strategy into account.