SCML 2022 League
One of the ANAC 2022 Competition Leagues (@ IJCAI 2022)

SCML 2022 Final Results

Oneshot Track

# AgentTeam InstituteScore WinningsLinks
1 PatientAgent Chris Mascioli and Amy Greenwald Brown University 11430 500€ Video, Slides
2 GentleS Takumu Shimizu Tokyo University of Agriculture and Technology 10625 300€ Video, Slides
3 AgentSAS Shiraz Nave, Amit Dayan, Sariel Turay Bar Ilan University 10593 200€

Standard Track

# AgentTeam InstituteScore WinningsLinks
1 Lobster Ito Nobuhiro and Takanobu Otsuka Nagoya Institute of Technology -96 500€ Video, Slides
2 M5 Kazuki Komori Tokyo University of Agriculture and Technology -155 300€ Video, Slides
3 Artisan Kangaroo Koki Katagiri and Takanobu Otsuka Nagoya Institute of Technology -186 200€

Collusion Track

# AgentTeam InstituteScore WinningsLinks
M5 Kazuki Komori Tokyo University of Agriculture and Technology 700 200€ Video, Slides

NEWS

  • 2022.7.25 The schedule for ANAC 2022 was shifted by 45min to avoid conflicting with the opening ceremony of IJCAI. See the new ANAC program schedule here.
  • 2022.06.29 ANAC 2022 will be held in Schubert2 (Classroom, 94sqm, 40 chairs, ~12 tables) during morning-afternoon session (first half) of July 26th.
  • 2022.06.04 The final SCML newsletter for 2022 was sent. Make sure to register to receive important announcements and newsletters.
  • 2022.06.04 Initial agent submission deadline was extended to June 8th.
  • 2022.05.19 We started a discord channel for up to date announcements and news: Join Us
  • 2022.05.18 Today, we released a new version of negmas (0.9.5), scml (0.5.5), scml-agents (0.1.7) and scml-vis (0.1.11). Please upgrade your development environment to this version. This update fixes a bug in score calculation. You should at least run: pip install -U scml
  • 2022.05.16 Please check the FAQs if you are facing trouble uploading your agent. Example questions answered there are:
  • 2022.05.16 A new version of the SCML platform with bug-fixes and quality of life improvements was releasted (v0.5.4). Please be sure to upgrade your development environment
  • 2022.05.16 The first SCML newsletter for 2022 was sent. Make sure to register to receive important announcements and newsletters.
  • 2022.05.14 Testing agents upon submission was fixed. Please re-upload your agent if in doubt.
  • 2022.03.09 The online competition will start on 2022.3.17

Finalists (SCML 2022)

ID Corresponding Author Institute Country Agent Name Track
20108 Eran Hirsch Bar Ilan University Israel AdamAgent Oneshot
20109 Ruben Wolhandler Bar Ilan University Israel EVEAgent Oneshot
20124 Yosef Zumer Bar Ilan University Israel Learning Adaptive Oneshot
20126 Shiraz Nave Bar Ilan University Israel AgentSAS Oneshot
20136 Ryoga Miyajima Tokyo University of Agriculture and Technology Japan Agent RM Oneshot
20138 Takumu Shimizu Tokyo University of Agriculture and Technology Japan GentleS Oneshot
20142 Chris Mascioli Brown University USA PatientAgent Oneshot
20143 Ryota Arakawa Tokyo University of Agriculture and Technology Japan AgentNeko Oneshot
20146 Ito Nobuhiro Nagoya Institute of Technology Japan Lobster Standard
20102 Sakamoto Natsumi Nagoya Institute of Technology Japan SkyAgent Standard
20008 Koki Katagiri Nagoya Institute of Technology Japan ArtisanKangaroo Standard
58 Kazuki Komori Tokyo University of Agriculture and Technology Japan M5 Std/Collusion
20080 Umut Çakan Ozyegin University Turkey CharliesAgent Std/Collusion

Official Participants (SCML 2022)

ID Corresponding Author Institute Country Agent Name Track
20096 LI ZONGCAN Kyoto University Japan AdaptiveQlagent Oneshot
20098 Ben Boren Bar Ilan University Israel Agent 125 Oneshot
20107 LiorS Bar Ilan University Israel AdaptivePercentile Oneshot
20108 Eran Hirsch Bar Ilan University Israel AdamAgent Oneshot
20109 Ruben Wolhandler Bar Ilan University Israel EVEAgent Oneshot
20124 Yosef Zumer Bar Ilan University Israel Learning Adaptive Oneshot
20126 Shiraz Nave Bar Ilan University Israel AgentSAS Oneshot
20129 Yosef Bar Ilan university Israel MMMPersonalized Oneshot
20136 Ryoga Miyajima Tokyo University of Agriculture and Technology Japan Agent RM Oneshot
20138 Takumu Shimizu Tokyo University of Agriculture and Technology Japan GentleS Oneshot
20142 Chris Mascioli Brown University USA PatientAgent Oneshot
20143 Ryota Arakawa Tokyo University of Agriculture and Technology Japan AgentNeko Oneshot
20016 Sagi Bar Ilan University Israel Agent 74 Oneshot
20044 Yuchen Liu Kyoto University Japan UcOneshotAgent Oneshot
20064 Assaf Tirangel Bar Ilan University Israel Agent 112 Oneshot
20146 Ito Nobuhiro Nagoya Institute of Technology Japan Lobster Standard
20100 Shunya Hibino Nagoya Institute of Technology Japan SalesAgent Standard
20101 Takuma Miwa Nagoya Institute of Technology Japan SmartAgent Standard
20102 Sakamoto Natsumi Nagoya Institute of Technology Japan SkyAgent Standard
20008 Koki Katagiri Nagoya Institute of Technology Japan ArtisanKangaroo Standard
58 Kazuki Komori Tokyo University of Agriculture and Technology Japan M5 Std/Collusion
20080 Umut Çakan Ozyegin University Turkey CharliesAgent Std/Collusion

This is the home of the Supply Chain Management League one of ANAC 2022 leagues @ IJCAI 2022.

The main motivation behind the SCM league is to increase the relevance of autonomous negotiation research by focusing on real-world scenarios that are characterized by situated negotiations, and complex dynamic utility functions.

The agent needs not only decide how to negotiate in a predefined single negotiation session, but when to join negotiations, and how to coordinate the behavior of its negotiators across multiple concurrent negotiations.

It is highly recommended to register your interest in the league by registering to this website by April 30th (No need to upload an agent by that time). It is mandatory to upload a preliminary version of the agent by June 8st.

Please note that the score on the live-competition will not impact in any way your final score in the official competition to be announced at IJCAI 2022.

The live competition is run using fewer configurations than the official competition to facilitate faster feedback when submitting new agents. This may lead to different results in the official competition.

Changes from SCML 2021

  • Agent scores in the collusion track will be the difference between what they get controlling three factories on the same production level and what they get controlling individual factories at the same configuration.
  • In the one-shot track, agents based on the OneshotSyncAgent need not handle cases where the offers from partners are received in more than one call to counter_all()

Getting started and getting help

  1. The first thing you need to do is to read the game overview for the one shot track and/or the standard/collusion tracks.
  2. If you are not registered here, do so to received updates and be able to submit your agents later here.
  3. After deciding which track(s) to participate in, check there detailed description( OneShot Standard/Collusion).
  4. Next, Check the tutorials. You can find video tutorials and consult the documentation and we are happy to see you joining the discussions.
  5. Next, Download the appropriate skeleton (OneShot or standard/collusion) and test it. You will find a full description on how to do that in the README as well as the docstring on top of myagent.py in the skeleton .
  6. Happy hacking :-) If you have any questions, bug reports, feature requests, etc, you can open an issue on the SCML GitHub page

Sponsors

Links

Important Dates

Registration (Optional)April 30th
Preliminary SubmissionJune 8st
Last Online TournamentJune 9th
Final SubmissionJune 10th
Report SubmissionJune 17th
Finalist AnnouncementJuly 1st
Winner AnnouncementJuly 26th

Statistics

Past Competitions