Detailed information for this page is currently under preparation.
The content will be announced and updated on this website once it is officially confirmed.
Please check this page regularly for future updates.
Further details will be made available in due course.
AI Competition · 2026
AI in Games Contest 2026
AI in Games Contest 2026 invites participants to design intelligent agents
capable of strategic decision-making, adaptation and autonomous competition
in the Commander game environment.
Terahertz Science and Applications Research Center, Beijing Institute of Technology (Zhuhai)
Guiping Lu is a Professor and Master's Supervisor at the Terahertz Science and Applications Research Center, Beijing Institute of Technology (Zhuhai). Her work combines artificial intelligence research with teaching innovation and student development. Under her guidance, students have earned more than 60 awards at provincial level or above in competitions including RoboMaster and the International Competition of Advanced Robotics and Simulation Technology.
Over the past five years, she has led more than 10 provincial teaching and research projects. Her academic output includes 30 papers, 20 granted invention patents and eight monographs and textbooks as lead editor. Her textbook Fundamentals of Artificial Intelligence Technology was published by Tsinghua University Press in July 2025.
Her honors include selection for Guangdong's Qianbaishi Talent Program and recognition as a Guangdong Nanyue Outstanding Teacher. She has earned first prizes in a university teaching-skills competition and the professor category of a teaching-innovation competition, alongside three second-prize teaching achievement awards. She also contributes to professional committees, academic project review and regional AI development.
Professional appointments
Member, Artificial Intelligence Technology and Applications Committee, China Institute of Communications
Member, Engineering Education Committee, China Institute of Communications
Member, Equipment Structural Health Monitoring and Early Warning Branch, China Instrument and Control Society
Member, Artificial Intelligence and Robotics Education Committee, China Education Strategy Society
Council Member, Guangdong Engineering Graphics Society
Academic Project Review Expert, Guangdong Association for Science and Technology
Expert, Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence Industry Think Tank
Member, Review Committee for High-Level Academic Exchange Projects in Zhuhai
Guangdong Science and Technology Commissioner
Additional honors
Recognized for teaching excellence by the City of Zhuhai and her university
Third Prize, Guangdong Multimedia Courseware Competition
Contest Expert
Minling Zhu
Associate Professor
Beijing Information Science and Technology University
Minling Zhu is an Associate Professor at Beijing Information Science and Technology University, where she leads the university's Artificial Intelligence and Embedded Systems Innovation Team. Her research focuses on artificial intelligence and image technology, bringing together academic research, industry collaboration and practical technology transfer.
She has led or contributed to more than 10 national and Beijing-funded research projects and led over 10 industry projects. Her research record includes more than 60 papers in academic journals and conferences, with multiple papers recognized among the top 1% most cited in Essential Science Indicators (ESI). Her intellectual property portfolio includes more than 10 granted invention patents and software copyrights in total, with patent research successfully translated into commercial use.
She serves on China's National Technical Committee for Information Technology Standardization and the Smart Education Committee of the Chinese Association of Automation. She is also a senior member of the Chinese Association of Automation.
Contest Expert
Genjing Chang
Executive Deputy Secretary-General, Committee on Artificial Intelligence and Robotics Education
Chinese Society of Educational Development Strategy
Genjing Chang works across artificial intelligence education, industry collaboration and innovation development. He serves as Executive Deputy Secretary-General of the Committee on Artificial Intelligence and Robotics Education of the Chinese Society of Educational Development Strategy, Deputy Secretary-General of the Committee on Big Data Systems and Simulation of the China Simulation Federation, and Deputy Director of the Embodied Intelligence Committee of the China Association of Machinery Industry Education.
He is also Executive Director of the Industry-University-Research Collaboration Center at the Yangtze River Delta Institute of Information and Intelligent Innovation, Executive Vice President of the Yangtze River Delta Data Elements Research Institute, and Deputy Secretary-General of the Beijing Internet of Things Society. These appointments connect his work in AI education with collaboration among educational institutions, research organizations and industry.
His university engagements include serving as an Industry Professor for the Artificial Intelligence Program Cluster at Nanjing Vocational College of Information Technology and an Entrepreneurship Mentor at Beijing Information Science and Technology University. He also holds expert, mentoring and advisory appointments at institutions across China, covering robotics education, academic program development and industry-education integration. As a Contest Expert, he brings this breadth of educational and industry experience to the AI in Game Contest.
Professional appointments
Executive Deputy Secretary-General, Committee on Artificial Intelligence and Robotics Education, Chinese Society of Educational Development Strategy
Deputy Secretary-General, Committee on Big Data Systems and Simulation, China Simulation Federation
Deputy Director, Embodied Intelligence Committee, China Association of Machinery Industry Education
Executive Director, Industry-University-Research Collaboration Center, Yangtze River Delta Institute of Information and Intelligent Innovation
Executive Vice President, Yangtze River Delta Data Elements Research Institute
Deputy Secretary-General, Beijing Internet of Things Society
Industry Professor, Artificial Intelligence Program Cluster, Nanjing Vocational College of Information Technology
Entrepreneurship Mentor, Beijing Information Science and Technology University
Maker Expert, Henan Institute of Technology
Industry Professor, Anhui Province
Academic Program Development Adviser, Chongqing Electronic Science and Technology Vocational University
Specially Appointed Expert, Tianjin University of Technology
External Mentor, Xi'an Jiaotong-Liverpool University
Industry Mentor, Anhui Sanlian University
Robotics Education Expert, Hubei University of Education
Industry-Education Integration Adviser, Hangzhou Normal University
Contest Information
Competition Date
October 30 – November 2, 2026
The competition will be held from October 30 to November 2, 2026.
Venue
Pending
Detailed venue information will be published once confirmed.
Registration
Pending
Registration procedures and submission instructions will be announced soon.
About the Contest
The contest is based on Commander, a real-time strategy
environment with turn-based tactical elements. The game is played on a
hexagonal map in which players expand territory, occupy strategic locations,
accumulate forces and attempt to locate and capture their opponents'
headquarters.
Participants do not directly control the game. Instead, each team develops
an autonomous intelligent agent that observes information available within
its own field of vision and makes decisions during each game step.
The Challenge
Successful agents must combine strategic expansion, resource management,
navigation, defence and decision-making under incomplete information.
Strategic Decision-Making
Decide when and where to expand, defend territory, move forces and engage
opponents.
Partial Observation
Agents can only use information visible from their own controlled areas,
requiring decisions under uncertainty.
Autonomous Competition
Once a match begins, intelligent agents independently interact with the
game environment through the provided interfaces.
AI Training & Evaluation
Participants may develop rule-based agents or use machine-learning and
reinforcement-learning approaches.
How to Get Started
Download Commander II
Download and fully extract the Commander II desktop package on a Windows
x64 computer.
Run the Example Match
Use the included sample agents to verify that the local game environment
is working correctly.
Develop Your AI Agent
Create an autonomous agent using Lua or Python and implement your own
decision-making strategy.
Test and Evaluate
Use single-match mode for debugging and automated evaluation for repeated
matches and strategy comparison.
Improve and Train
Advanced participants may use the provided training API and reinforcement
learning examples to develop more sophisticated agents.
Commander AI Platform
The contest platform provides the tools required for agent development,
testing, evaluation and AI training.
Single Match
Run matches between multiple agents for testing, debugging and observation.
Automated Evaluation
Run repeated matches and collect wins, draws and execution results.
Lua & Python
Develop competition agents using either Lua or Python.
Training API
Interact with a step-based environment designed for AI training.
Reinforcement Learning
Example workflows include DQN, MaskablePPO and self-play training.
Logs & Replays
Review match logs, evaluation results and game recordings during development.
Game Overview
Game Environment
Strategic competition on a hexagonal-grid map.
Player Objective
Expand territory, accumulate forces and capture opponents' headquarters.
Information
Agents operate under limited visibility and may only use information
available within their own field of vision.
Agent Languages
Lua and Python.
Development
Rule-based strategies, search algorithms, machine learning and
reinforcement learning approaches may be developed using the provided
interfaces.
Evaluation
Agents can be tested through individual matches and repeated automated
evaluations before the competition.
AI Development & Training
Agent Development
The platform includes example agents demonstrating basic exploration,
greedy expansion and path-finding strategies.
Participants can build upon these examples and introduce defence,
force allocation, target prioritisation, historical state, opponent
modelling and AI-based decision systems.
Model Training
The training environment provides observations, legal-action masks,
rewards and episode termination information through a dedicated Python
training interface.
Example training workflows include DQN, MaskablePPO and two-agent
self-play.
Downloads
Contest software, technical documentation and additional materials will be
published here as they become available.
More contest materials are coming soon.
Additional documentation, development resources and competition-related
files will be added to this section when available.
System Requirements
The current Commander II desktop package is designed for
Windows x64. Participants should fully extract the package
to a writable local directory before running the application.
Windows systems may require .NET Framework 4.6.2 or later and Microsoft
Edge WebView2 Runtime. These components are normally available on current
Windows 10 and Windows 11 systems.
Further Information
The venue and registration procedure are currently being finalised.
Updated information will be published on this page once confirmed.
Participants are encouraged to check this page regularly for the latest
announcements and additional contest materials.
AI in Games Contest 2026 · Information on this page is subject to further
updates by the organising committee.
