Research Lead: David Pynadath
ICT’s Social Simulation Lab models and simulates human social interaction within AI systems. Research includes both descriptive models for simulating human-like decision-making and prescriptive models for human-machine teaming with autonomous agents.
The core of these models is decision-theoretic AI as a foundation for a theory of mind that can be reused across different domains and use cases. Data-driven algorithms provide an automated mechanism for building and validating social simulations. Abstraction and approximation methods allow the models to scale to larger and more complex social decision-making.
The social-simulation architecture, PsychSim, provides an open-source library of these algorithms. It has been used for large-scale simulations of urban populations (e.g., hurricane response, patterns of life, terrorist attacks) and small scale human-machine teaming (e.g., search-and-rescue). It has also been applied in interactive training games for urban stabilization (UrbanSim), cross-cultural negotiation (BiLAT), foreign language and culture (TacLang), and avoiding risky behavior (SOLVE).
A new investigation into human-machine teaming seeks to build an AI model of teamwork into PsychSim that can give autonomous systems the social skills to be good teammates when working together with people. Another effort will expand the domains of PsychSim’s application to cybersecurity, with descriptive models of attackers and prescriptive models of defenses against them.