SCML 2025
Part of the ANAC 2025 Competition @ IJCAI 2025, Montreal, Canada

We thank all our participants for their great efforts. The winners were announced in Montreal at the ANAC session @ IJCAI which was held on August 21, 2025 (15:00-17:30 ) in Room 515AB. The schedule for official IJCAI competitions can be found here. IJCAI took place in the Palais des congrès, Montreal, Canada between August 16th and August 22nd, 2025.

The slides for the winner announcement can be found here

All agent source code and reports can be found in the scml-agents GitHub repository.

Oneshot Track Final Results

Rank Agent Score Leader Institute Country Winnings Links
CautiousOneShotAgent 1.091540 Ryoga Miyajima TUAT Japan 2024 Winner Report Video Slides
1 CostAverseAgent 1.089634 Yuzuru Kitamura TUAT Japan 300€ Report Video Slides
1 Rchan 1.089524 Shota Takayama TUAT Japan 300€ Report Video Slides
1 AlmostEqualAgent 1.089231 Rikuto Takano and Takeaki Sakabe NIT Japan 300€ Report Video Slides

Standard Track Final Results

Rank Agent Score Leader Institute Country WinningsLinks
1 AS0 1.008782 Atsunaga Sadahiro TUAT Japan 500€ Report Video Slides
PenguinAgent 0.992153 Gou Kazusa NIT Japan 2024 Winner Report Video Slides
2 XenoSotaAgent 0.96013 Sota Sakaguchi and Takanobu Otsuka NIT Japan 300€ Report Video Slides
3 Ultra Super Miracle Sora Final Agent Z 0.936938 Sora Nishizaki and Takanobu Otsuka NIT Japan 200€ Report Video Slides

SCML: Finalists

Agent Institute Country Leader Team Track
CostAverseAgent TUAT Japan Yusuru Kitamura Team Yusuru OneShot
Rchan TUAT Japan Shota Takayama takafam OneShot
AlmostEqualAgent NIT Japan Takano Rikuto NIT OneShot
DistRedistAgent TUAT Japan Haijime Endo Team Ukku OneShot
HorYamaAgent Kyoto University Japan Hauaki Horinouchi Team Star Up OneShot
AS0 TUAT Japan Atsunaga Sadairo Team Atsunaga Standard
XenoSotaAgent NIT Japan Sota Sakaguchi SotaWorks Standard
UltraSuparMiracleSoraFinalAgentZ NIT Japan Sora Nishizaki Team 254 Standard
PriceTrendStdAgent NIT Japan Kawasaki Yuta Team 280 Standard

SCML 2025 Participants

OneShot

Agent Team Leader Institute Country Team Name
Rchan Takayama TUAT Japan takafam
PPOAgent Shoma Mizuno NIT Japan Team 293
AlmostEqualAgent Takano Rikuto NIT Japan Team 284
AnalysisAgent Eito Sugita NIT Japan Team 283
HoriYamaAgent Hayaki Horinouchi Kyoto University Japan Team STAR UP
MATAgent_Prelim Tyrone Serapio Brown University USA MAT
DistRedistAgent Hajime Endo TUAT Japan Team Ukku
CostAverseAgent Yuzuru Kitamura TUAT Japan TeamYuzuru
CautiousOneShotAgent Ryoga Miyajima TUAT Japan Team Miyajima
MatchingPennies Akash Singirikonda Brown University USA Team 193

Standard

Agent Team Leader Institute Country Team Name
AS0 Atsunaga Sadahiro TUAT Japan Team ATSUNAGA
PriceTrendAgent (Slides) Kawasaki Yuta NIT Japan Team 280
PonponAgent Kento Fukuda NIT Japan Team 255
UltraSuperMiracleSoraFinalAgentZ Sora Nishizaki NIT Japan Team 254
XenoSotaAgent Sota Sakaguchi NIT Japan SotaWorks
KATSUDON Yamadori Kohki NIT Japan MISOKATSU-TEISYOKU
LitaAgentYR YIHENG TANG Kyoto University Japan Team 276
Penguin Agent GouKazusa NIT Japan Team Penguin
CautiousStdAgent Ryoga Miyajima TUAT Japan Team Miyajima

NEWS

  • August 26th, 2025 All code and reports of all agents submitted to SCML 2025 are now available at the scml-agents repo alongside agents from previous year. You can also pip install scml-agents to get them.
  • August 19th, 2025 The ANAC session in Montreal will be Thursday August 21 from 3pm to 5:30pm at room 515AB. You can also join us at the first Competition booth (booth 7) anytime from 9am to 5pm.
  • May 30th, 2025Submission deadline was extended to June 10th.
  • March 18th, 2025The CFP is out
  • May 20th, 2024 Agents submitted to SCML 2024 are now available in the scml-agents package (v0.4.9). You can install them using "pip install scml-agents". For more information, check the source code at GitHub
  • May 19th, 2024 The results of SCML 2024 are now available here

Getting started and getting help

  1. The first thing you need to do is to read the game overview for the track you plan to submit to. You can check this year's rules for the one shot track and/or the standard track.
  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 or Standard ).
  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 Classic, RL or Standard Classic) 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

Links

Important Dates (GMT)

Preliminary SubmissionJune 8th, 2025
Final SubmissionJune 10th, 2025
Report SubmissionJune 13th, 2025
Finalist AnnouncementJune 24th, 2025
Travel SupportTBD
Winner AnnouncementAugust 16th, 2025

Statistics (2025)

Statistics (Total)

Past Competitions