Automated Negotiating Agents Competition (ANAC2021)

To be held at IJCAI2021 in Online, on August 25th 2021 as a part of the IJCAI competition challenge

NEWS


 

Overview of ANAC2021


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 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 five different negotiation research challenges:

We expect innovative and novel agent strategies will be developed, and the submitted ANAC 2021 agents will serve as a negotiating agent repository to the negotiation community. The researchers can develop novel negotiating agents and evaluate their agents by comparing their performance with the performance of the ANAC 2021 agents.

Leagues in ANAC2021


Automated Negotiation League

Design a negotiation agent for bilateral negotiation that can learn from every previous encounters while the tournament progresses.

Human-Agent League

Explore the strategies, nuances, and difficulties in creating realistic and efficient agents whose primary purpose is to ‚Äčnegotiate with humans.‚Äč

Supply Chain Management League

Design and build an autonomous agent that negotiates on behalf of a factory manager situated in a supply chain management simulation.

Werewolf Game League

Build an agent that is able to build consensus with other actors (who are potentially deceptive), identify agents of the opposing team and coordinate to vote them out of the game.

 

Winners


You can find the winners for each league.

Automated Negotiation League

  1. AlphaBIU; Bar-Ilan University
  2. MatrixAlienAgent; University of Tulsa
  3. TripleAgent; Utrecht University

Human-Agent League

  1. Agent Naji; Bar-Ilan University
  2. FairTrader; University of Tulsa
  3. Doctor Strange; The College of Management Academic Studies

Supply Chain Management League

[Oneshot Track]

  1. Agent 112; Bar-Ilan Univrsity
  2. Gentle; Tokyo University of Agriculture and Technology
  3. Agent 74; Bar-Ilan University & UcOneshotAgent; Kyoto University
[Standard Track]
  1. M4; Tokyo University of Agriculture and Technology
  2. CharliesAgent; Ozyegin University+Brown University
  3. ArtisanKangaroo; Nagoya Institute of Technology
[Collusion Track]
  1. M4; Tokyo University of Agriculture and Technology
  2. CharliesAgent; Ozyegin University+Brown University
[BIRD Innovative Award]
  • GodfatherGoldfish; Brown University

Werewolf Game League

[AIWol NLP Task]

  1. Udon; Independent
  2. CanisLupus; Independent
  3. AzuEmon; Kyoto University
[Protocol Task]
  1. ICE/toku, Tokushima University
  2. TOT, Yamagata University
  3. KP22, Kougakuin University

 

Finalists


You can find the finalist for each league. The ordering does not reflect the actual ranking. They are sorted alphabetically. Note that the actual ranking will be announced in ANAC session during the IJCAI 2021.

Automated Negotiation League

8 submissions

  • AlphaBIU; Bar-Ilan University
  • MatrixAlienAgent; University of Tulsa
  • TripleAgent; Utrecht University

Human-Agent League

11 submissions

  • Agent Naji; Bar-Ilan University
  • Doctor Strange; The College of Management Academic Studies
  • FairTrader; University of Tulsa

Supply Chain Management League

33 submissions

[Oneshot Track]

  • Agent 74; Bar-Ilan University
  • Agent 112; Bar-Ilan Univrsity
  • Gentle; Tokyo University of Agriculture and Technology
  • GodfatherGoldfish; Brown University
  • StagHunter; University of Michigan
  • The Sopranos 78; Bar-Ilan Univrsity
  • UcOneshotAgent; Kyoto University
  • Zilberan; Bar-Ilan University
[Standard Track]
  • ArtisanKangaroo; Nagoya Institute of Technology
  • CharliesAgent; Ozyegin University+Brown University
  • M4; Tokyo University of Agriculture and Technology
  • Mediocre; Ozyegin University
  • PAIBIU; Bar Ilan University
[Collusion Track]
  • ArtisanKangaroo; Nagoya Institute of Technology
  • CharliesAgent; Ozyegin University+Brown University
  • M4; Tokyo University of Agriculture and Technology
  • Mediocre; Ozyegin University

Werewolf Game League

32 submissions

[AIWol NLP Task]

  • AzuEmon; Kyoto University
  • BIU wolfs; Bar Ilan University
  • CanisLupus; Independent
  • ForestLab; Yokohama University
  • Kanolab; Shizuoka University
  • Udon; Independent
[Protocol Task]
  • CanisLupus, independent
  • HALU, Kyoto University
  • Hideto, Yamagata University
  • ICE, Tokushima University
  • karma, Chiba Intstitute of Technology
  • KP22, Kougakuin University
  • OKAMI, Bar -Ilan University
  • Sashimi, University of Tsukuba
  • SORA, Yamagata University
  • SYu, Yamagata University
  • toku, Tokushima University
  • Tomato, Independent
  • Tomatoken, Kougakuin University
  • TOT, Yamagata University
  • wasabi, Independent

 

ANAC2021 Program (Tentative)


Wednesday, 25th of August 2021 @Blue 3(You can attend the ANAC 2021 session through IJCAI 2021 virtual chair)

UTC CET(UTC+2) Turkey(UTC+3) Japan(UTC+9) EST(UTC-4)
Welcome: 10 min 8:00am-8:10am 10:00am 11:00am 5:00pm 4:00am
Automated Negotiation League: 50 min 8:10am-9:00am 10:10am 11:10am 5:10pm 4:10am
Break: 15 min 9:00am-9:15am 11:00am 12:00am 6:00pm 5:00am
WereWolf Game League: 50 min 9:15am-10:05am 11:15am 12:15pm 6:15pm 5:15am
Break: 15 min 10:05am-10:20am 12:05am 1:05pm 7:05pm 6:05am
Supply Chain Management League: 50 min 10:20am-11:10am 12:20am 1:20pm 7:20pm 6:20am
Break: 20 min 11:10am-11:30am 1:10pm 2:10pm 8:10pm 7:10am
Human-Agent League: 50 min 11:30am-12:20am 1:30pm 2:30pm 8:30pm 7:30am
Discussion: 40 min 12:20pm-1:00pm 2:20pm 3:20pm 9:20pm 8:20am

The session in each league will be include:

 

Sponsors


NEC-AIST AI Cooperative Research Laboratory BIRD INITIATIVE

CWI

 

Organization


ANAC Board Members

League Organizers

Sponsorship Chair in ANAC2021

Scientific Advisory Board

 

Contact


For any questions of ANAC2021, the main contact is Dr. Reyhan Aydogan reyhan.aydogan[at]ozyegin.edu.tr