Multiagent Automated Negotiation Theories and their Evaluations
| Project/Area Number |
15H01703
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (A)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Nagoya Institute of Technology |
|---|
Principal Investigator |
Ito Takayuki 名古屋工業大学, 工学(系)研究科(研究院), 教授 (50333555)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
藤田 桂英 東京農工大学, 工学(系)研究科(研究院), 准教授 (00625676)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥43,550,000 (Direct Cost: ¥33,500,000、Indirect Cost: ¥10,050,000)
Fiscal Year 2017: ¥14,300,000 (Direct Cost: ¥11,000,000、Indirect Cost: ¥3,300,000)
Fiscal Year 2016: ¥14,300,000 (Direct Cost: ¥11,000,000、Indirect Cost: ¥3,300,000)
Fiscal Year 2015: ¥14,950,000 (Direct Cost: ¥11,500,000、Indirect Cost: ¥3,450,000)
|
|---|
| Keywords | 自動交渉 / エージェント / 交渉 / ゲーム理論 / 効用関数 / マルチエージェントシステム / メタ戦略 / プロトコル / 複雑な効用関数 / 合意形成 / 複数論点効用問題 / 多者間交渉問題 / 交渉シミュレータ / 機械学習による交渉戦略 / 自動交渉理論 / グラフ効用モデル / 交渉理論 / メタ交渉戦略 / 交渉シミュレーション / 国際自動交渉エージェント競技会 / 自動交渉エージェント / 離散効用空間 |
|---|
| Outline of Final Research Achievements |
The aim of this research is to deepen the automated negotiation theory and evaluation based on simulation on automated negotiations in the dispersed negotiation space. In this research, we clarified efficient utility models, negotiation strategies, and negotiation protocols. In particular, we achieved the following break-through results: (1) We proposed a new graph-based utility model which successfully represent very complex utility spaces. (2) We proved that meta negotiation strategy can work well in the particular group of negotiation agents. (3) We implemented a new negotiation simulation environment which can use machine learning technologies. (4) We continuously held the ANAC international automated negotiation competitions where we examined the advantage of the proposed models, strategies, and protocols.
|
Report
(4 results)
Research Products
(48 results)
-
-
-
-
-
-
-
-
-
-
-
[Journal Article] Automated Negotiating Agents Competition (ANAC)2017
Author(s)
Catholijn M. Jonker, Reyhan Aydogan, Tim Baarslag, Katsuhide Fujita, Takayuki Ito and Koen Hindriks
-
Journal Title
Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17)
Pages: 5070-5072
Related Report
Peer Reviewed / Int'l Joint Research
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
