Agent-Based Modeling Using Erlang

There is a conceptual gap between real world systems and their models created using differential equations. Numerous systems, such as traffic flow, financial markets, neural networks... are all naturally composed of agents interacting with each other and the environment, from which the behavior of such systems emerges. The more complex the interactions and agents, the more difficult, and even impossible, it becomes to model them using averages and standard mathematical approaches like sets of differential equations. A more direct approach to modeling such complex systems is by modeling the agents themselves, and letting them interact with each other and the environment, with the system's behavior then emerging naturally. This approach is called Agent Based Modeling (ABM), and the conceptual gap between real world phenomena produced by interacting agents and their respective ABMs is lower than the models created using sets of differential equations. The removal of this conceptual gap through the use of ABMs allows us to tackle larger and more complex problems and explore emergent behavior more easily. Unfortunately, ABMs and the programming languages used to create them do not have a 1-to-1 mapping, and thus, producing a conceptual gap between the two. This paper attempts to present and make a claim that we can eliminate this conceptual gap by using an actor model based concurrency oriented programming language called Erlang. In this paper we discuss how Erlang fits into ABM and Multi-Agent Simulation systems, and what features it possesses that make it such a perfect tool for the job.