On finding effective courses of action in dynamic uncertain situations

The objective of this research develops a methodology for finding effective courses of action (COAs) in a dynamic uncertain situation. The dynamic situation is modeled using a probabilistic modeling and reasoning framework, referred to as Timed Influence Nets (TINs). The TIN-based framework helps a system analyst in connecting a set of actionable events and a set of desired effects through chains of cause and effect relationships. Once a TIN is built, the optimization task confronted by the analyst is to identify a course of action that maximize some pre-determined metrics related to the likelihood of achieving a desired effect. An Evolutionary Algorithm is used to accomplish this task and the methodology is named ECAD-EA (Effective Courses of Action Determination using Evolutionary Algorithms). The methodology generates multiple COAs that are close enough in terms of the likelihood of achieving the desired effect. The purpose of generating multiple COAs is to give several alternatives to a decision maker. Moreover, the alternate COAs could be generalized based on the relationships that exist among the actions and their execution timings. While determining an effective course of action in a given situation, a system analyst has to consider several temporal/causal constraints that are present among actionable events. This research develops a constraint specification language that would help a system analyst in specifying these constraints. A heuristic approach, named SAF (Sets of Actions Finder) is presented for the problem of best or close-to-best sets of actions determination in untimed Influence Nets. The approach enhances the analysis capability of Influence Nets by allowing an analyst to observe the combined impact of actions on the desired effect in contrast to the sensitivity analysis (SA) that allows the analyst to evaluate actions' individual impacts only. (Abstract shortened by UMI.)