Enhancing Multi-Agent Based Simulation with HumanLike Decision Making Strategies (original) (raw)

Towards an Integrated Agent and Environment Architecture for Simulation of Human Decision Making and Behavior

2019

Dieses Paper prasentiert die IDEATE Architektur, eine auf den Sozialwissenschaften basierende Architektur zur Abbildung von Entscheidungsfindung und Verhalten von intelligenten Agenten. Besonderer Fokus der Architektur liegt auf der unmittelbaren Berucksichtigung von personlichen und gesellschaftlichen Uberzeugungen und Meinungen bei Entscheidungsfindung und der damit verbundenen Wechselwirkung von Agent und Umwelt. Daruber hinaus schlagt dieses Paper ein geeignetes Verfahren zur Formalisierung der Uberzeugungen und Meinungen zur Anwendung der IDEATE Architektur in einem spateren Simulationssystem vor.

Simulating human behaviors in agent societies

ABSTRACT Asincreasing,numbers ,of processors ,and ,agents ,pervade ,the human environment, societies comprising both humans and agents will emerge. Presently, it is unknown how a person might fair in such mixed societies. For the societies to operate ,effectively and efficiently, it is important for the humans and agents to recognize and understand ,each other’s behavior. This paper provides ,an initial step in that ,understanding via ,two ,contributions: (1) we provide models, within a limited domain, for agents that behave like humans ,and ,(2) we present ,the results of simulated interactions between,the human-like agents and a variety of purely rational agents. Our models for the behaviors of people are based onrecent,sociological research by Simpson ,and Willer [10] that explores humans’ cooperative prosocial behavior, a conceivably non-rational process. Modeling human,behaviors presents a means ofexploring and understanding motivations, consequences, and resolutions to human-a...

Command Agents with HumanLike Decision Making Strategies

2007

Human behavior representation in military simulations is not sufficiently realistic, specially the decision making by synthetic military commanders. In order to address some of these deficiencies, we have developed a computer implementation of Recognition Primed Decision Making (RPD) model using Soar cognitive architecture and it is referred to as RPD-Soar agent in this paper. The proposed implementation is evaluated using prototypical scenarios arising in command decision making in tactical situations. Due to the ability of the RPD-Soar agent to mentally simulate applicable courses of action it is possible to use the agent without further training. These agents can be further enhanced to exhibit various levels of expertise. The preliminary results clearly demonstrate the ability of the model to represent human behavior variability within and across individuals. The results also show the change in decision making strategy with experience.