Human-AI Teaming (STRONG)
Humans do team well while AI agents do not. One example of this is the Dota 2 AI Open AI Five: Five AI agents would be in the game as five top Dota 2 players in the world, and they were broken into different teams with other human agents to fight against each other. However, the agents do not collaborate well. The overall goal of the project, STRONG (Strengthening Teamwork for Robust Operations in Novel Groups), is to probe the future of HMT (human-machine teaming) and to develop natural task general human-guided machine learning capabilities for future scenarios of teaming.
Here are three strands for this:
Strand 1: Design New Game - Speculative Game Design for Futuristic HMT. We’ll be looking at the idea of speculative game design - we think about not just how teaming looks now but also in the future.
Strand 2: Semantics of Human-Guided Machine Learning. One can do Interactions (rewards and punishment), interventions, and demonstrations to guide the agent which is based on machine learning models, like the Q-learning-based one.
Strand 3: Human-Guided Machine-Learning Agent Development. We’ll be looking at how to build agents that could adapt what the means ones want to teach on the fly and apply them across multiple games.
Related Publications
Ziyu Li, Noor Hammad, Qiao Zhang, Chunyi Wang, Erik Harpstead (2025). Vertical Farm: A Unified Testbed to Address Challenges in Human-Agent Teaming Research. Proceedings of the 13th International Conference on Human-Agent Interaction.
Qiao Zhang, Glen Smith, Ziyu Li, Yuxuan Dong, Erik Harpstead, Christopher J. MacLellan (2025). Dice Adventure: An Asymmetrical Collaborative Game for Exploring the Hybrid Teaming Effects. Proceedings of the 20th International Conference on the Foundations of Digital Games. 🏆 Best Paper Award
Qiao Zhang, Christopher J. MacLellan (2025). Think and Play: Designing and Evaluating Human-AI Teaming Dynamics in Gaming Environments. Proceedings of the 2025 AAAI Symposium Series.
Leon Lange, Qiao Zhang, Christopher J. MacLellan, Ying Wu (2025). Training Humans for Robust Human-Agent Teaming: Knowing When to Engage with an AI Partner. Proceedings of the 2025 AAAI Symposium Series.
Ying Wu, Leon Lange, Jacob Yenney, Qiao Zhang, Erik Harpstead (2024). Scaffolded versus Self-Paced Training for Human-Agent Teams. Proceedings of the 12th International Conference on Human-Agent Interaction.
Qiao Zhang (2024). Working with My TeammAItes: Exploring Human-AI Teaming Dynamics through Gaming Environments. 19th International Conference on the Foundations of Digital Games.
Qiao Zhang (2023). Understanding Human-AI Teaming Dynamics through Gaming Environments. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment.
Erik Harpstead, Kimberly Stowers, Lane Lawley, Qiao Zhang, Christopher J. MacLellan (2023). Speculative Game Design of Asymmetric Cooperative Games to Study Human-Machine Teaming. Proceedings of The First Workshop on Human-AI Interaction through Play @ FDG 2023.