This site is best viewed using a newer browser that supports style sheets

TAC LOGO WELCOME TO THE TRADING AGENT COMPETITION
Competitive Benchmarking for The Trading Agent Community
 LOGIN | SEARCH | FAQ | LEGAL NOTICES
TAC 2012
Info & Call
Registration
Participants
TADA-12 *
* link to external site
 
   

Call for Participation: TAC-2012

Thirteenth Annual Trading Agent Competition, June 4 - 5, 2012
Valencia, Spain --- Collocated with AAMAS 2012, the 11th Conference on Autonomous Agents and Multi-agent Systems, and with EC'12, the Thirteenth ACM Conference on Electronic Commerce


Trading in electronic markets is an increasingly commonplace economic activity, as well as a topic of special interest within the AI, Electronic Commerce, and Multiagent Systems (MAS) research communities.

We invite you to participate in the Thirteenth Annual Trading Agent Competition (TAC-12), to be held in May and June of 2012, with the finals taking place during the AAMAS-12 conference in Valencia, preceded by qualifying and seeding rounds in May and early June. You may register for the competition through 15 April 2012.

Building on the success of previous Trading Agent Competition events, this year's event is again designed to spur research on common problems, promote definitions of benchmarks and standard problem descriptions, and showcase current technologies.

The competition will pit software agents, developed by research groups, students, and others from all over the world, against each other in challenging competitive simulation scenarios. These scenarios are designed to present competing agents with difficult decision problems and admit a wide variety of potential bidding and negotiation strategies.

The 2012 competiton will include four games:

  1. Power TAC. Sustainable energy systems of the future will need more than efficient, clean, low-cost, renewable energy sources; they will also need efficient price signals that motivate sustainable energy consumption as well as a better real-time alignment of energy demand and supply. In Power TAC, agents act as retail brokers in a local power distribution region, purchasing power from a wholesale market as well as from local sources, such as homes and businesses with solar panels, and selling power to local customers and into the wholesale market. Retail brokers must solve a supply-chain problem in which the product is infinitely perishable, and supply and demand must be exactly balanced at all times.
    Power TAC Game Master is Wolf Ketter, Erasmus University, Rotterdam. Full documentation and software are available at the powertac.org website.
  2. TAC Ad Auctions (AA). In the TAC/AA game, agents representing Internet advertisers bid for search-engine ad placement over a range of interrelated keyword combinations. A back-end search-user model translates placement over each simulated day to impressions, clicks, and sale conversions, yielding revenue for the advertiser. Advertiser strategies combining online data analysis and bidding tactics compete to maximize profit over the simulated campaign horizon.
    TAC AA Game Master is Michael Wellman, University of Michigan. Documentation and software for participating in the AA Tournament can be found at the tradingagents.org site.
  3. TAC Market Design (reverse TAC, or "CAT"). CAT software agents represent market makers whose goals are to attract potential buyers and sellers as customers, and then to match buyers with sellers. The market makers compete with one another in doing this, such as the London Stock Exchange competes with the NYSE for the business of stock traders.
    CAT Game Master: Tim Miller, University of Melbourne. Documentation and software for participating in the CAT Tournament are accessible via sourceforge.
  4. TAC Supply Chain Management (SCM). TAC/SCM simulates a dynamic supply chain environment where agents compete to secure customer orders and components required for production of these orders. The game captures many of the complexities of actual supply chains, where both demand and supply fluctuate and each manufacturer has limited production capacity. There are also two SCM Challenge events that can be run if there is a clear expressed interest: a Procurement Challenge and a Prediction Challenge; these will take place if enough teams (minimum 6) register for them.
    TAC SCM Game Master is Vedran Podobnik, University of Zagreb. Software and documentation include an open source agent framework for TAC SCM, and sample agents, and an updated SCM server and log-analysis tool, with examples.

The qualifying and seeding rounds will be held in May and early June, and the first day of the final rounds is scheduled to coincide with TADA/AMEC, the Joint Workshop on Trading Agent Design and Analysis and Agent-Mediated Electronic Commerce workshop to be held at AAMAS'12.

To register for TAC-12, please fill out the registration form before 15 April 2012.

The entry fee will be US$250 per team to enter one game, or $400 for all TAC games.

The entry fee (for one game) is waived for teams who send a representative to the TAC finals at AAMAS 2012, if that representative registers for the TADA workshop (in case a team participates in more than 1 game, registration cost is reduceed to US$150).

Note: Please send any questions regarding the fees to tac [at] tradingagents.org. Groups unable to afford the entry fee may also contact tac [at] tradingagents.org for special consideration.

Exact dates for the qualifying and seeding rounds will soon be posted on this site, and sent to the tac-discuss mailing list. You may subscribe by sending an email to tac-discuss-request (at) umich.edu, subject "subscribe".

Sponsored by the Association for Trading Agent Research.


Copyright © 2001-2012 SICS AB. All Rights Reserved.
For questions about Trading Agent Competition or about this web site, contact tac-dev [at] sics.se