AIIDE-20 Workshop on
Artificial Intelligence for Strategy Games
(October 19, 2020 on Google-Meet)

News

• [Oct-06] Updated schedule
• [May-17] PC list updated
• [Apr-26] Webpage Created

Background

In 2012-2019 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.

A few years ago, we broadened the workshop scope a bit 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. This idea apparently paid off as last year we had 7 papers presented.

The goal of this follow-up 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.

Workshop Format

This one-day workshop will consist of paper presentations on strategy game related AI topics (listed below), RTS game competition reports (StarCraft Broodwar and μRTS), a commented man-machine StarCraft match (most likely replays), perhaps an invited presentation, and a discussion on future research.

Contributions will be peer-reviewed and meet AAAI workshop standards.

Topics

This 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:

• Reinforcement Learning in Strategy Games
• State and Action Abstractions
• Heuristic Search Applied to High-Branching Factor Domains
• Player Modelling, Co-operation and Exploitation
• Plan and Goal Recognition
• Game Balancing
• Level Generation
• Motion Planning
• High-Level Strategic Planning
• Dealing with Imperfect Information

Tentative Workshop Schedule

1055 :::Welcome
1100 Presentations (papers 3+5+6)
1200 :::Break
1215 Presentations (papers 1+4+7)
1315 :::Lunch
1415 Tournament Reports
1445 Show-and-Tell / future research directions, part 1
1555 :::Break
1610 Show-and-Tell / future research directions, part 2
1700 :::Wrap-Up

• Alexander - Stratega
• Diego - Tribes Demo
• Costa - OpenGym micro-RTS environment https://wandb.ai/vwxyzjn/gym-microrts/reports/Gym-microrts-s-V2-Benchmark--VmlldzoyNTg5NTA
• Dave

• Benchmarks: Should we keep focusing on StarCraft and try to play better using less computational resources? or should we look at something more general? E.g., learning to play a variety of RTS games?
• Transformers: Can we bring the Transformer paradigm to games? It has had great success in NLP
• Multi-action turn-based games (e.g. Civilization). How do those compare to RTS games AI-wise?
• How to speed up learning? (transfer learning, curriculum learning?)
• Are there any games left that humans like to play which can be used as AI benchmark?

Accepted Papers (6)

• p1: "A Reasoning-based Defogger for Opponent Army Composition Inference under Partial Observability” Hao Pan pdf
• p3: "MCTS pruning in Turn-Based Strategy Games”, Yu-Jhen Hsu, Diego Perez-Liebana pdf
• p4: "Transfer Learning Between RTS Combat Scenarios Using Component-Action Deep Reinforcement Learning” Richard Kelly and David Churchill pdf
• p5: "Bandit-Based Policy Optimization for Monte Carlo Tree Search in RTS Games” Zuozhi Yang and Santiago Ontañón pdf
• p6: "Action Guidance: Getting the Best of Training Agents with Sparse Rewards and Shaped Rewards” Shegyi Huag and Santiago Ontañón pdf
• p7: “STRATEGA - A General Strategy Games Framework” Alexander Dockhorn, Jorge Hurtado-Grueso, Dominik Jeurissen, Diego Perez-Liebana pdf

Important Dates

• Early submissions (for those whose academic year ends on June 30):
  • Submission deadline: June 7, 2020
  • Acceptance notification: June 30, 2020
• Regular submissions
  • Submission deadline: August 15, 2020
  • Acceptance notification: September 1, 2020
• Camera-ready version: September 15, 2020

Submission Format

• PDF format
• at most 7 pages (including all references)
• 12-point font, two-column, single spaced format, LaTeX preferred (AAAI style file preferred)
• blind review process, please don't mention author names
• submit by email to michael.buro@gmail.com AND santi.ontanon@gmail.com (subject "WORKSHOP PAPER")

Workshop Programming Committee

The following people served on the workshop PC last year and will likely help this year as well:

• Michael Buro Co-Organizer (Univ. of Alberta)
• Santiago Ontañón Co-Organizer (Google)
• David Churchill PC (Memorial Univ.)
• Nathan Sturtevant PC (Univ. of Alberta)
• Levi Lelis PC (Univ. of Alberta)
• Florian Richoux PC (Univ. de Nantes)
• Mike Preuss PC (Univ. Münster)
• Nicolas Barriga PC (Univ. de Talca)
• Kevin Dill PC (Lockheed Martin)
• Julian Mariño PC (Univ. de São Paulo)
• Gabriel Synnaeve PC (Facebook)
• Zeming Lin PC (Facebook)
• Julian Togelius PC (NYU)
• Yaser Norouzzadeh PC (Tilburg University)
• Pieter Spronck PC (Tilburg University)
• Hector Munoz-Avila PC (Lehigh University)
• Simon Lucas PC (Queen Mary Univ.)