16th International Conference on Cognitive Modeling
We use the ACT-R cognitive architecture (Anderson, 2007) to explore human-AI collaboration. Computational models of human and AI behavior, and their interaction, allow for more effective development of collaborative artificial intelligent agents. With these computational models and simulations, one may be better equipped to predict the situations in which certain classes of intelligent agents may be more suited to collaborate with people. One can more tractably understand and predict how different AI agents affect task behavior in these situations. To simulate human-AI collaboration, we are developing ACT-R models that work with more traditional AI agents to solve a task in Project Malmo (Johnson et al., 2016). We use existing AI agents that were originally developed as the AI portion of the Human-AI collaboration. In addition, creating a model in ACT-R to simulate human behavior gives us the opportunity to play out these interactions much faster than would be possible in real time.
Brill, Z. M., & Dancy, C. L. (2018). Simulating Human-AI Collaboration with ACT-R and Project Malmo. In proceedings of the 16th International Conference on Cognitive Modeling, Madison, WI: University of Wisconsin, 9-10.