Ninth International Automated Negotiating Agents Competition

To be held at IJCAI 2018 in Stockholm, Sweden, in July 2018 as part of the IJCAI competition track.

News

July 24th, 2018: The winners and the final results of ANAC2018 were uploaded.

July 14th, 2018: ANAC2018 program is uploaded.

June 1st, 2018: The finalists of Repeated Multilateral Negotiation and Diplomacy league were announced.

May 20th, 2018: The deadline for submitting agents was extended to May 31th, 2018

May 14th, 2018: Student Travel Support was updated.

Feburuay 22th, 2018: ANAC2018 webpage was launched.

 

 

ANAC2018 Winners

Repeated Multilateral Negotiation League

(Individual Utility)
  1. AgreeableAgent2018 by Sahar Mirzayi University of Tehran, Iran
  2. meng wan by Meng Wan, Hui Cui, University of Southampton, UK
  3. Beta One by Alper Şekerci, Abdulkadir Nurkalem, Özyeğin University, Turkey
(Social Welfare)
  1. AgentHerb by Alon Stern, Amit Moryossef, Yehudit Reyzer, Karin Dahan, Bar Ilan University, Israel
  2. Agent33 by Nagoya Institute of Technology, Japan
  3. Sontag by Tokyo University of Agriculture and Technology, Japan
Slides of Repeated Multilateral Negotiation League Results

 

Human-Agent Negotiation League

  • The winners of the 2nd Annual Human-Agent League of ANAC 2018: Gilad Yadgar, Daniel Juravski, Natali Tshuva, Chen Rozenshtein, and Keren Babay, with their agent "Equalist", representing Bar Ilan University in Israel
  • The runners up, Dongsheng Xie and Jianye Hao of Tianjin University (Agent XDS), and Siqi Chen, XinYi Li, ZhiHao Dou, and JiaXu Li of Southwest University (Agent Athena).

 

Diplomacy League

Results of Diplomacy League in ANAC2018

 

 

ANAC2018 Program

Tuesday 17, 16:20 - 19:00 ANAC Competition (Room K13)

  • 16:20-16:25 Welcome and Introduction
  • 16:25-16:50
    • Human-Agent League Awards Ceremony by Johnathan Mell
    • Human Agent League Winner: Equalist by Gilad Yadgar, Bar Ilan University
    • Human Agent League Runner-up: XDS by Dongsheng Xie, Tianjin University
    • Human Agent League Runner-up: Athena by XinYi Li, Southwest University
  • 16:50-17:05
    • Diplomacy League Challenges by Dave de Jonge
    • Diplomacy League Outstanding Strategy: Gunma by Ryohei Kawata (Tokyo University of Agriculture and Technology, Japan)
  • 17:05-17:25
    • Genius League Awards Ceremony by Katsuhide Fujita and Reyhan Aydogan
    • Genius Winner Strategy in Individual Utility Category
    • Genius Winner Strategy in Product Utility Category
  • 17:30-17:50 Dr. Tim Baarslag’s presentation
  • 17:50-18:10 NEC-AIST Presentation by Dr. Satoshi Morinaga: Slide
  • 18:10-18:40 Talks given by Scholars
    • BetaOne by Abdulkadir Nurkalem (Özyeğin University, Turkey)
    • ConDAgent by Konstantia Xenou (Technical University Of Crete, Greece)
    • Yeela by Tiktinsky Aryeh (Bar-Ilan University, Israel)
    • meng wan by Meng Wan, Hui Cui (University of Southampton, UK)
    • SMAC_Agent by Bram Renting (Delft university of Technology, Netherlands)
    • PonpokoRampage by Takaki Matsune (Tokyo University of Agriculture and Technology, Japan)
    • Sontag by Ryohei Kawata (Tokyo University of Agriculture and Technology, Japan)
  • 18:40-19:00 Discussions for future leagues

 

 

Overview of ANAC2018

The Automated Negotiating Agent Competition (ANAC) is an international tournament that has been running since 2010 to bring together researchers from the negotiation community. ANAC provides a unique benchmark for evaluating practical negotiation strategies in multi-issue domains and has the following aims:

  • to provide an incentive for the development of effective and efficient negotiation protocols and strategies for bidding, accepting and opponent modeling for different negotiation scenarios;
  • to collect and develop a benchmark of negotiation scenarios, protocols and strategies;
  • to develop a common set of tools and criteria for the evaluation and exploration of new protocols and new strategies against benchmark scenarios, protocols and strategies;
  • to set the research agenda for automated negotiation.
The previous 7 competitions have spawned novel research in AI in the field of autonomous agent design which are available to the wider research community.

This year, we introduce four different negotiation research challenges:

  • Repeated multilateral negotiation for arbitrary domains (Genius framework)
  • Negotiation strategies for the Diplomacy game (Bandana framework)
  • Human-agent negotiation (IAGO framework)
  • Supply Chain Connection and Management through Negotiations
We expect innovative and novel agent strategies will be developed for ANAC2018. After the competition, submitted agents will be made available to the negotiation community as part of a negotiating agent repository within the aforementioned frameworks. The researchers can develop novel negotiating agents and evaluate their agents by comparing their performance with the performance of the ANAC 2018 agents.

 

 

1- ANAC Repeated Multilateral Negotiation League

In multilateral negotiation league, entrants will to design and implement an intelligent negotiating agent, which negotiates with two opponents and is able to learn from its previous negotiations. The participants will develop their agents in GENIUS platform. Challenges regarding this league are to design winning strategies for bidding, opponent modeling and bid acceptance strategies when negotiating repeatedly with agents in a multilateral setting.

Participants will submit their agent source code and class files (in a .zip or .jar package) as well as a new multi-player negotiation scenario for three parties (i.e., domain.xml, profile1.xml, profile2.xml, and profile 3.xml). That is, each group will also submit a negotiation domain description and three conflicting preference profiles represented by means of linear additive utility. Submission package: Please submit your application though the following link: https://tinyurl.com/GENIUSANAC2018

More details can be found by following this link: Repeated Multilateral Negotiation League CFP

GENIUS platform: http://ii.tudelft.nl/genius/

 

Qualification Round Results

We selected the finalists in individual utility and social welfare category based on the qualification round results.

    (Individual Category)
  • meng wan, University of Southampton, UK
  • IQSun2018, University Of Tehran, Iran
  • PonPokoRampage, Tokyo University of Agriculture and Technology, Japan
  • AgreeableAgent2018, University of Tehran, Iran
  • Shiboy, Nagoya Institute of Technology, Japan
  • Beta One, Özyeğin University, Turkey
  • AgentNP1, privateer, Japan
  • GroupY, Özyeğin University, Turkey
  • Sontag, Tokyo University of Agriculture and Technology, Japan
    (Social Welfare)
  • AgentHerb, Bar Ilan University, Israel
  • FullAgent, Bar Ilan University, Israel
  • IQSun2018, University Of Tehran, Iran
  • ConDAgent, Technical University Of Crete, Greece
  • AgreeableAgent2018, University of Tehran, Iran
  • Yeela, Bar-Ilan University, Israel
  • AgentNP1, privateer, Japan
  • Sontag, Tokyo University of Agriculture and Technology, Japan
  • Agent33, Nagoya Institute of Technology, Japan

The details of the qualification round are as follows: here

 

 

2- Negotiation Strategies for Diplomacy Game

In the Diplomacy game league, entrants to the competition have to develop a negotiation algorithm for the game of Diplomacy. Diplomacy is a strategy game for 7 players. Each player has a number of armies and fleet positioned on a map of Europe and the goal is to conquer half of the "Supply Centers". What makes this game very interesting and different from other board games, however, is that players need to negotiate with each other in order to play well. Players may team up and create plans together to defeat other players.

Every participant in this competition must implement a negotiation algorithm using the BANDANA framework. This negotiation algorithm will then be combined with an existing non-negotiating agent (the D-Brane Strategic Module) to form a complete negotiating Diplomacy player.

Please send all your source in a zip file to: d.dejonge@westernsydney.edu.au

More details can be found by following this link: Diplomacy Challenge CFP

BANDANA platform: http://www.iiia.csic.es/~davedejonge/bandana/

 

 

3- Human-agent Negotiation

The Human-Agent Negotiation (HAN) league explores the strategies, nuances, and difficulties in creating realistic and efficient agents whose primary purpose is to negotiate with humans. Human negotiation includes features not often seen in agent-agent negotiation, including retractable and partial offers, emotion exchange, preference elicitation strategies, favors-and-ledgers behavior, and more. To understand these features and better create agents that use them, this competition is designed to be a showcase for the newest work in the negotiating agent community.

This year, the HAN league will focus on negotiation over time, with agents competing with humans over the course of three interactions, and trying to get the highest score over all three negotiations combined. Each entrant will submit an agent that will be tested against human subjects in a study run through the University of Southern California. All agents must be compliant with the IAGO (Interactive Arbitration Guide Online) framework and API, which will allow standardization of the agents and efficient running of subjects on MTurk.

Each agent will be uploaded to the IAGO website, using the dedicated uploader. For any questions relating to IAGO or the submissions process, you may email iago@ict.usc.edu.

More details can be found by following this link: Human-agent Negotiation League

IAGO website, including installation instructions and user guides:http://people.ict.usc.edu/~mell/IAGO

 

 

Prize

The prize money will be at least 500 euros for each league. The prize will be shared among the top agents - winners.

 

 

Student Travel Support

We are pleased to announce that we are able to provide scholarships to support student participants in the Automated Negotiating Agents Competition (ANAC) 2018, to be held at IJCAI 2018 in Stockholm, Sweden, as part of the IJCAI competition track. The purpose is to enable BSc., MSc., and graduate students to travel and participate in ANAC and the AAMAS/IJCAI conference. To be eligible, you must be registered as a full-time student at a higher education institution (e.g. University); and participate in the ANAC 2018 competition as a team member and/or presenter.

The order of priority for awards is as follows:

  1. Student finalists of the leagues of ANAC 2018;
  2. Students presenting a paper or poster about their negotiating agent at AAMAS/IJCAI 2018 or the International Workshop on Automated Negotiation (ACAN 2018);
  3. Students presenting their work at the ACAN workshop;

Given the limited budget, priority will be given to high-ranking finalists of each league. To the extent that funds allow, we also hope to support students whose research will benefit from attendance at ANAC 2018. We anticipate different levels of funding based on anticipated costs, ranking within the competition, and so on, covering travel costs and/or attendance fees.

Application: To apply, you are required to apply for a Student Scholarship as part of the submission form of your ANAC agent at: https://tinyurl.com/GENIUSANAC2018. You will need to provide your participation details for ANAC 2018 as well as a pdf with a scanned student ID card certifying you are registered as a full-time student. Please note that participation in the student scholarship program carries with it an obligation to be present at the ANAC 2018 session during the ACAN workshop (July 13/14) or the main IJCAI conference (July 16/17). Please submit your application by May 21, 2018 (11:59pm, Hawaiian time) together with your agent submission via the web form shown above. We will notify you of the decision as part of the announcements of the finalist (end of June 2018 at the latest).

 

 

Organising Committee

Main Organising Committee

  • Dr. Reyhan Aydogan, Ozyegin University & Delft University of Technology
  • Dr. Tim Baarslag, Centrum Wiskunde & Informatica (CWI)
  • Prof. Dr. Katsuhide Fujita, Tokyo University of Agriculture and Technology
  • Prof. Dr. Takayuki Ito, Nagoya Institute of Technology
  • Prof. Dr. Catholijn Jonker, Delft University of Technology

Local Organising Committee

  • Dr. Reyhan Aydogan, Ozyegin University & Delft University of Technology
  • Dr. Tim Baarslag, Centrum Wiskunde & Informatica (CWI)
  • Prof. Dr. Katsuhide Fujita, Tokyo University of Agriculture and Technology
  • Dr. Dave de Jonge, Western Sydney University
  • Johnathan Mell, The University of Southern California

 

 

Sponsors

AI Journal

TU Delft

NEC - AIST AI Cooperative Research Laboratory

 

Contact

For any questions of ANAC2018, the main contact is Dr. Reyhan Aydogan <reyhan.aydogan[at]ozyegin.edu.tr>