Probabilistic Relational Agent-based Models
This work addresses a foundational problem in computational modeling for researchers in AI and simulation, offering a novel integration that could enhance efficiency and theoretical soundness.
The paper tackles the challenge of integrating agent-based and probabilistic models by introducing Probabilistic Relational Agent-based Models (PRAM), which provide a probabilistic foundation for agent-based models and can be more efficient than traditional agent-based simulation.
PRAM puts agent-based models on a sound probabilistic footing as a basis for integrating agent-based and probabilistic models. It extends the themes of probabilistic relational models and lifted inference to incorporate dynamical models and simulation. It can also be much more efficient than agent-based simulation.