Variability in Behavior of Command Agents with Human-Like Decision Making Strategies

Human behavior representation in military simulations is not sufficiently realistic, specially the decision making in synthetic military commanders. One of the problems in decision making is that the decisions are predictable. In order to address some of these deficiencies, we have developed a computer implementation of Recognition Primed Decision (RPD) making 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 for the agent to handle new situations very effectively using its prior knowledge. The variability in behavior within an agent is a desirable characteristic. Variability in agents may be produced through randomness but randomness also introduces undesirable behavior. The observed variability in the RPD-Soar agent is due to reasonable but some times sub-optimal choices given to the agent. RPD-Soar agent developed in this paper exhibits the ability to change decision making strategy with experience. And the preliminary results clearly demonstrate the ability of the model to represent human behavior variability within and across individuals.