[agents] Call for Participation - Automated Negotiating Agent Competition - ANAC 2017 at IJCAI

[Reyhan Aydogan]

*The Eighth International Automated Negotiating Agent Competition
(ANAC)Website: http://web.tuat.ac.jp/~katfuji/ANAC2017/
<http://web.tuat.ac.jp/%7Ekatfuji/ANAC2017/>Held at IJCAI 2017 in
Melbourne, Australia in August 2017 as part of the IJCAI competition track:
http://ijcai-17.org/competitions.html
<http://ijcai-17.org/competitions.html>Motivation, impact, and expected
outcomesThe 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 three
different negotiation research challenges: - Repeated multilateral
 negotiation for arbitrary domains (Genius framework
<http://ii.tudelft.nl/genius/>)- Negotiation strategies for the Diplomacy
game (Bandana framework <http://www.iiia.csic.es/%7Edavedejonge/bandana>)-
Human-agent negotiation (IAGO framework
<http://people.ict.usc.edu/%7Emell/IAGO>)We expect innovative and novel
agent strategies will be developed for ANAC 2017. 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 2017 agents.The finalists are very welcome to submit an article
explaining their negotiation strategy to the International Third Workshop
on Conflict Resolution in Decision Making (COREDEMA 2017) and present their
strategy at the workshop, which will be held in conjunction with IJCAI in
Melbourne . http://ii.tudelft.nl/coredema2017
<http://ii.tudelft.nl/coredema2017>Challenges1. Repeated multilateral
negotiation for arbitrary domainsIn 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.GENIUS is a
Java-based negotiation platform in which you can create negotiation domains
and preference profiles as well as develop negotiating agents. The platform
allows you to simulate automated negotiation sessions and run tournaments.
More details can be found by following this link: -
http://ii.tudelft.nl/genius/ <http://ii.tudelft.nl/genius/> - For
frequently asked questions: http://tinyurl.com/ANAC2017GeniusFAQ
<http://tinyurl.com/ANAC2017GeniusFAQ> - Send your questions:-
reyhan.aydogan at ozyegin.edu.tr <reyhan.aydogan at ozyegin.edu.tr> -
T.Baarslag at cwi.nl <T.Baarslag at cwi.nl>- katfuji at cc.tuat.ac.jp
<katfuji at cc.tuat.ac.jp> 2. Negotiation strategies for the Diplomacy gameIn
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. BANDANA is a Java
framework designed for the development of automated agents that play the
game of Diplomacy. It comes with a tutorial that explains how you can
implement your own Diplomacy-playing, negotiating agents, and how you can
let them play a game of Diplomacy, or even an entire Diplomacy tournament.
BANDANA is an extension of the DipGame <http://www.dipgame.org/> framework.
However, it provides a new negotiation server and uses a simplified
negotiation language. More details can be found by following this link: -
http://www.iiia.csic.es/~davedejonge/bandana/
<http://www.iiia.csic.es/%7Edavedejonge/bandana/> - For frequently asked
questions: http://tinyurl.com/ANAC2017DiplomacyFAQ
<http://tinyurl.com/ANAC2017DiplomacyFAQ> - You can send your questions
to:- d.dejonge at westernsydney.edu.au <d.dejonge at westernsydney.edu.au> 3.
Human-agent negotiationThe Human-Agent Negotiation league  is proposed in
order to further explore the strategies, nuances, and difficulties in
creating realistic and efficient agents whose primary purpose is to
negotiate with humans.  Previous work on human-agent negotiation has
revealed the importance of several features not commonly present in
agent-agent negotiation, including retractable and partial offers, emotion
exchange, preference elicitation strategies, favors-and-ledgers behavior,
and myriad other topics.  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.The Human-Agent Negotiation
competition will involve each entrant submitting 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.
Agents will all be run on the same set of multi-issue bargaining tasks.IAGO
is a Java-based platform developed by Mell and Gratch at the University of
Southern California.  It is intended to serve as a testbed for Human-Agent
negotiation specifically.  IAGO is a web-based servlet hosting system that
provides data collection and recording services, a human-usable HTML5 UI,
and an API for designing human-like agents. More details can be found by
following this link: - http://people.ict.usc.edu/~mell/IAGO
<http://people.ict.usc.edu/%7Emell/IAGO>. - For an installation tutorial
and  frequently asked questions:IAGO Getting Started Guide
<http://people.ict.usc.edu/%7Emell/IAGO/tutorial.html> - Send your
questions:- iago at ict.usc.edu <iago at ict.usc.edu> PrizeThe prize money will
be 500 dollars for each league. The prize will be shared among the top
agents - winners.Competition ScheduleDeadline for submitting agents: June
1st, 2017Please fill out the intention form to participate
 (http://tinyurl.com/ANAC2017Intention
<http://tinyurl.com/ANAC2017Intention>) to be added to mailing list and
receive updates and answers to frequently asked questionsDiplomacy League:
Please send all your source in a zip file to:
d.dejonge at westernsydney.edu.au <d.dejonge at westernsydney.edu.au>Repeated
multilateral  negotiation League: Each participant is expected to submit a
negotiation scenario. That is, each group will submit a negotiation domain
description and three conflicting preference profiles represented by means
of linear additive utility. Submission package: The participants will
submit their agent source code and class files (in a .zip or .jar package)
as well as their negotiation scenario (i.e., domain.xml, profile1.xml,
profile2.xml, and profile 3.xml). Please send your submission package by 1
June, 2017 reyhan.aydogan at ozyegin.edu.tr <reyhan.aydogan at ozyegin.edu.tr>
and anac2017 at katfuji.lab.tuat.ac.jp
<anac2017 at katfuji.lab.tuat.ac.jp>.Human-Agent Negotiation League: Each
agent will be uploaded to the IAGO website
(http://people.ict.usc.edu/~mell/IAGO/uploads
<http://people.ict.usc.edu/%7Emell/IAGO/uploads>).  The upload link will be
made available closer to the submission deadline (June 1st, 2017).
  Instructions will be sent out on the mailing list along with further
details for checking compilation against reference libraries. Your
submission should include a single .zip file, which contains one or more
.java source files, as well as the qualified class name for your agent
(e.g., “edu.usc.ict.mylab.agents.WinningAgent”).  You should include the
class name both on the web form on the upload website  as well as in a
readme.txt file (along with any other information you may wish to
include).  You do NOT need to include any files within the provided
“edu.usc.ict.iago.views” package.  For any questions relating to IAGO or
the submissions process, you may email iago at ict.usc.edu <iago at ict.usc.edu>.
References on ANACSeveral papers have been published about the setup and
results of previous ANAC competitions: - The First Automated Negotiating
Agents Competition (ANAC 2010)
<http://ii.tudelft.nl/negotiation/images/3/34/ANAC2010.pdf> (ext. link
<http://link.springer.com/chapter/10.1007%2F978-3-642-24696-8_7>) - The
Second Automated Negotiating Agents Competition (ANAC2011)
<http://mmi.tudelft.nl/sites/default/files/The%20Second%20Automated%20Negotiating%20Agents-pub.pdf>
(ext. link <http://dx.doi.org/10.1007/978-3-642-30737-9_11>) - Evaluating
Practical Negotiating Agents: Results and Analysis of the 2011
International Competition
<http://mmi.tudelft.nl/sites/default/files/aij-anac2011-pub_0.pdf> (ext.
link <http://dx.doi.org/10.1016/j.artint.2012.09.004>) - A Baseline for
Non-Linear Bilateral Negotiations: The full results of the agents competing
in ANAC 2014
<http://users.ecs.soton.ac.uk/tb1m13/pub/A_Baseline_for_Non-Linear_Bilateral_Negotiations-The_full_results_of_the_agents_competing_in_ANAC_2014.pdf>
(ext. link <http://eprints.soton.ac.uk/399235/>) - The Automated
Negotiating Agents Competition, 2010-2015
<http://homepages.cwi.nl/%7Ebaarslag/pub/The_Automated_Negotiating_Agents_Competition-2010-2015.pdf>
(ext. link
<http://www.aaai.org/ojs/index.php/aimagazine/article/view/2609>)Website
URLFor more details, please visit the competition webpage : -
http://web.tuat.ac.jp/~katfuji/ANAC2017/
<http://web.tuat.ac.jp/%7Ekatfuji/ANAC2017/>*