<html><head></head><body><div>You are invited to submit an agent to the Supply Chain Management League (SCML) of the International Automated Negotiating Agents Competition (ANAC) as part of the AAMAS 2024 official competition track.<br></div><div class="gmail_signature"><div class="gmail_signature">ANAC is running since 2010 in conjunction with AAMAS/IJCAI and SCML is running as part of ANAC since 2019.</div><div class="gmail_signature">Check the competition website at <a href="https://scml.cs.brown.edu">https://scml.cs.brown.edu</a> for details</div><div class="gmail_signature">### The Challenge</div><div class="gmail_signature">Design and build an autonomous agent that negotiates on behalf of a factory manager situated in a supply chain management simulation.</div><div class="gmail_signature">The goal of a factory manager in SCML is to maximize its profit given its private production capabilities by negotiating trades with other agents. A factory manager can engage in several negotiations simultaneously, for which its utility functions are in general interdependent. These negotiations, and any ensuing contracts, are bilateral. Moreover, they are private to the agents involved.</div><div class="gmail_signature"><br></div><div class="gmail_signature">### New in 2024</div><div class="gmail_signature">- We provide support for developing agents using RL/MARL. SCML is now a gymnasium environment and we provide templates for developing and training models for the competition.</div><div class="gmail_signature">- The Standard track is completely re-designed to simplify its interface and development workflow while keeping the core of the challenge intact.</div><div class="gmail_signature"><br></div><div class="gmail_signature">### Negotiation Protocol</div><div class="gmail_signature"><br></div><div class="gmail_signature">Agents are factory managers that control factories with private manufacturing profiles which are revealed at the start of each simulation. Factory manager agents negotiate bilaterally with other agents to buy the necessary inputs to their manufacturing process, and to sell the outputs.</div><div class="gmail_signature"><br></div><div class="gmail_signature">All negotiations are carried out via the alternating offers protocol. This protocol specifies that two negotiators take turns making offers. One agent starts the negotiation with an opening bid, after which the other party can take the following actions:</div><div class="gmail_signature">- Accept the offer</div><div class="gmail_signature">- Make a counteroffer, thus rejecting and overriding the previous offer</div><div class="gmail_signature">- Walk away, thus declaring an end to the negotiation without having reached an agreement</div><div class="gmail_signature">This process is repeated until either an agreement is reached, or the deadline arrives. To reach an agreement, both parties must accept the offer. If no agreement has been reached by the deadline, the negotiation fails.</div><div class="gmail_signature">A single simulation runs for a predefined number of steps with an overall time limit of two hours. All negotiations are conducted for a predefined number of rounds of the alternating offers protocol (with a predefined time limit on each).</div><div class="gmail_signature">Factory manager agents are reset after each simulation. This means that they cannot learn from previous simulations. They can, however, accumulate information about agents during a simulation, as they know their negotiating partners’ names.</div><div class="gmail_signature"><br></div><div class="gmail_signature">### Platform</div><div class="gmail_signature">Entrants to the competition should develop and submit an autonomous agent that runs on NegMAS. NegMAS is a Python-based negotiation platform in which you can create simulated worlds, like the SCM world, populated with agents capable of engaging in multiple negotiations.</div><div class="gmail_signature"><br></div><div class="gmail_signature">### Submission and Live Competition</div><div class="gmail_signature">An unofficial live competition will be run this year, beginning January 8th. All participants are encouraged to upload early versions of their agents to the online submission site and are required to upload a working agent by April 1st. A leaderboard will be maintained, displaying the relative performance of all submitted agents, but no identifying information about the participating teams will be available. This website is also where the final versions of agents should be submitted for the official competition (at which point identifying information will become available).</div><div class="gmail_signature"><br></div><div class="gmail_signature">### Evaluation</div><div class="gmail_signature">The competition will be conducted in two rounds, a qualifying round and a final round. All entrants that are not judged to break any of the SCML and ANAC submission rules will be entered into the qualifying rounds. Top-scoring agents in the qualifying round will then be entered in the final round. The organizing committee maintains the right to require that agents surpass a minimum score threshold to advance to the finals or to win one of the prizes.</div><div class="gmail_signature">The teams that build the top-scoring agents will be notified in July, with the final results and awards announced at AAMAS 2024 in Auckland. It is expected that finalists will send a representative to the ANAC workshop at AAMAS 2024, whether it is virtual or in-person, where they will be given the opportunity to give a brief presentation describing their agent. Three awards will be announced at AAMAS 2024 (with associated monetary rewards) corresponding to the two tracks (Standard, and OneShot).</div><div class="gmail_signature">The latest version of the agent submitted before the competition deadline will be used in the SCM league unless participants opt-out of the official competition.</div><div class="gmail_signature"><br></div><div class="gmail_signature">### Resources</div><div class="gmail_signature">For more information about SCML, please refer to the competition's [main website](<a href="https://scml.cs.brown.edu">https://scml.cs.brown.edu</a>).</div><div class="gmail_signature"><br></div><div class="gmail_signature">### Questions and Answers</div><div class="gmail_signature">Please check our FAQ. You can post your questions there (preferable), or address any concerns you prefer to remain private to Yasser Mohammad.</div><div class="gmail_signature">### Organizing Committee</div><div class="gmail_signature">- Yasser Mohammad, NEC-AIST AI Collaborative Research Laboratory (main contact)</div><div class="gmail_signature">- Katsuhide Fujita, Tokyo University of Agriculture and Technology & NEC-AIST</div><div class="gmail_signature">- Amy Greenwald, Brown University</div><div class="gmail_signature">- Mark Klein, MIT</div><div class="gmail_signature">- Satoshi Morinaga, NEC-AIST AI Collaborative Research Laboratory</div><div class="gmail_signature">- Shinji Nakadai, NEC-AIST AI Collaborative Research Laboratory</div><div class="gmail_signature">### Important Dates</div><div class="gmail_signature">- Registration on the competition website (Recommended): March 21st, 2024</div><div class="gmail_signature">- Preliminary submission deadline (REQUIRED): **March 23rd, 2024**</div><div class="gmail_signature">- Final submission deadline: **April 3rd, 2024**</div><div class="gmail_signature">- Academic Report submission deadline: **April 5th 2024**</div><div class="gmail_signature">### Sponsors</div><div class="gmail_signature">- [NEC-AIST AI Cooperative Research Laboratory](<a href="https://www.airc.aist.go.jp/en/project/overview.html">https://www.airc.aist.go.jp/en/project/overview.html</a>)</div><div class="gmail_signature">The organizing committee would like to thank Brown University for hosting the online submission website at [<a href="https://scml.cs.brown.edu">https://scml.cs.brown.edu</a>](<a href="https://scml.cs.brown.edu">https://scml.cs.brown.edu</a>).</div><div><br></div>
</div></body></html>