The Fighter Aircraft LCS: A Case of Different LCS Goals and Techniques

A system employed by the authors to acquire novel fighter aircraft manoeuvres from combat simulation is more akin to the traditional LCS model than to more recent systems. Given the difficulties often experienced in LCS research on simple problems, one must ask how a relatively primitive LCS has had consistent success in the complex domain of fighter aircraft manoeuvring. This paper presents the fighter aircraft LCS, in greater detail than in previous publications. Positive results from the system are discussed. The paper then focuses on the primary reasons the fighter aircraft LCS has avoided the difficulties of the traditional LCS. The authors believe the system's success has three primary origins: differences in credit assignment, differences in action encoding, and (possibly most importantly) a difference in system goals. In the fighter aircraft system, the goal has been simply the discovery of innovative, novel tactics, rather than online control. The paper concludes by discussing the most salient features of the fighter aircraft learning system, and how those features may be profitably combined with other LCS developments.