[please check for updates often]
From 2012-2017 successful workshops on AI for adversarial real-time games were held at AIIDE in response to the considerable interest in the subject and the limited time for reporting on the annual StarCraft competition in the main AIIDE conference.
Since 2018, we've broadened the workshop scope to cover AI for all kinds of strategy games in the hope to attract more submissions and to spark discussions between research groups focusing on board game, real-time strategy game, and general video game AI.
The goal of the SG workshop is to again bring together AI researchers and game AI programmers from industry, who are interested in strategic game AI, to present and exchange ideas on the subject, and to discuss how academia and game companies can work together to improve the state-of-the-art in AI for games.
This one-day workshop will consist of paper presentations on strategy game related AI topics (listed below), game competition descriptions (StarCraft Broodwar), show-and-tell presentations, and a discussion on future research.
Contributions will be peer-reviewed and meet AAAI workshop standards. Accepted workshop papers will be published as a single CEUR proceedings book.
The SG workshop welcomes original research contributions, position papers, competition AI system descriptions, and post-mortem game analyses in the area of AI for strategy games --- including modern video strategy games (such as FPS and RTS games), and turn based games and puzzles. Topics include, but are not restricted to:
Competitive esports is a growing worldwide phenomenon now rivaling traditional sports, with over 450 million views and $1 billion US dollars in revenue each year. Despite this significant popularity, much of the world remains unaware of esports — and in particular, research on and for esports is still extremely scarce compared to esports’ impact and potential. The goal of the esports analytics workshop is to begin to address this research gap, specifically looking at the research surrounding the use of esports data and AI. However, as this workshop has never before been run at AIIDE, for this first year, we are running in combination with the Strategy Games Workshop to help raise awareness and begin to build a community. As a part of the combined event, the Esports Analytics (EA) Workshop will bring in an invited speaker and host an informal discussion regarding the future of the workshop.
Presenter: Amine Issa of Mobalytics (mobalytics.gg)
Title: "The Consumer Side of Esports Analytics"
Abstract: Mobalytics is focused on delivering insights to all players regardless of their skill level, from the elite professionals to the average joes struggling to improve. This talk will highlight the key learnings from 6 years of building the platform around major esports titles like League of Legends, and also draw upon previous experience as a player playing professionally.
Bio: Amine Issa earned his doctorate at the Mayo Clinic researching the extremes of human performance, with his findings powering development of technology in mobile health and remote monitoring. He also spent decades playing video games, and competed professionally for a couple years. He came to believe that there are many broader lessons in performance that can be learned from the arena of esports. He was able to channel both his performance and gaming passions to found Mobalytics, a performance assessment and optimization platform for gamers.
GMT PDT
(GMT-7)
1525 0825 Welcome [Derek,Michael,Ben,Erica]
[Session 1: accepted papers; Michael]
1530 0840 (25+5 P2) Niklas Zwingenberger: "Transformers as Policies for Variable Action Environments"
1600 0915 (20+5 SAT2) Debraj Ray: "Strategic local navigation using RL in an adversarial RTS games environment"
1630 0940 (25) Break
[Session 2: Esports Analytics; Ben,Erica]
1640 1005 (50) Invited Talk: Amine Issa: "The Consumer Side of Esports Analytics"
1740 1055 (5) Break
[Session 3: Late paper and show-and-tell-1; Derek]
1750 1100 (25+5 P3) Abhijeet Krishnan: "Synthesizing Chess Tactics from Player Games"
1820 1125 (20+5 SAT1) Jose Antonio Solar Zavala: "Towards semi-exhaustive procedural content generation for Safari Rush Hour puzzles"
1845 1155 (15) Break
[Session 4: Show-and-tell-2 and competiton report; Michael]
1910 1210 (25+5 P1) Jay Ahn: "Baba is Smart"
1935 1240 (20+5 SAT3) Costa Huang: "Entity-oriented reinforcement learning for RTS games"
2000 1305 (20+5 CR) Dave Churchill: "StarCraft BroodWar Competition Report"
2030 1330 (10) Break
[Session 5: Show-and-tell-3; Derek]
2040 1340 (20+5 SAT4) Rubens Moares: "Choosing Your Opponents Well: How to Guide the Synthesis of Programmatic Strategies"
2105 1405 (20+5 SAT5) Ho-Taek Joo, Sung-Ha Lee, Cheong-mok Bae, Kyung-Joong Kim: "Learning to spectate games for Esports using object detection mechanism"
2130 1430 (10) Short Break
[Session 6: Show-and-tell-4 and discussion; Derek[,Michael],Ben,Erica]
[Please send an email to mburo@ualberta.ca AND dmartin7@ncsu.edu if you'd like to share your work in this session providing a title as soon as possible. This will help us plan this session]
2140 1440 (65) Audience show-and-tell and group discussion: research directions
after 1500 (20+5 SAT6) Levi Lelis: "Show Me the Way! Hierarchical Search for Synthesizing Programmatic Strategies"
2310 1610 Wrap-Up [Derek,Michael,Ben,Erica]
2315 1615 Future of the AIIDE Esports Analytics Workshop Discussion [Ben,Erica]
-2400 -1700
Please let us know ahead of time (by emailing mburo@ualberta.ca) if you'd like to show-and-tell your current work, i.e., briefly describe it and perhaps show a few slides or a software demo to get a discussion going. This will help us with time management.
Please also let us know by email what topics you'd like to talk about in the discussion session.
The following people served on the workshop PC last year and will likely help this year as well: