Generation and analysis of multiple futures with swarming agents

Most agent-based modeling techniques generate only a single trajectory in each run, greatly undersampling the space of possible trajectories. Swarming agents can explore a great many alternative futures in parallel, particularly when they interact through digital pheromone fields. These fields and other artifacts developed by such a model can be interpreted as probability fields. This interpretation not only allows us to derive more information from them than swarming models usually yield, but also facilitates integrating such models with probability-based AI mechanisms such as HMM's or Bayesian networks. Categories and Subject Descriptors I.2.11 [Computing Methodologies]: Distributed Artificial Intelligence

• Type: Conference
• Year: 2010
• Where: ATAL
• Authors: H. Van Dyke Parunak
• Keywords: Agent-based Modeling, ATAL 2010, Digital Pheromone Fields, Intelligent Agents, Most Agent-based Modeling