In adversarial environments, one side could gain an advantage by identifying the opponent's strategy. For example, in combat games, if an opponents strategy is identified as overly aggressive, one could lay a trap that exploits the opponent's aggressive nature. However, an opponent's strategy is not always apparent and may need to be estimated from observations of their actions. This paper proposes to use inverse reinforcement learning (IRL) to identify strategies in adversarial environments. Specifically, the contributions of this work are 1) the demonstration of this concept on gaming combat data generated from three pre-defined strategies and 2) the framework for using IRL to achieve strategy identification. The numerical experiments demonstrate that the recovered rewards can be identified using a variety of techniques. In this paper, the recovered reward are visually displayed, clustered using unsupervised learning, and classified using a supervised learner.

In this paper, we introduce a non-linear Lanchester model of NCW-type and investigate an optimization problem for this model, where only the Red force is supplied by several supply agents. Optimal fire allocation of the Blue force is sought in the form of a piece-wise constant function of time. A threatening rate is computed for the Red force and each of its supply agents at the beginning of each stage of the combat. These rates can be used to derive the optimal decision for the Blue force to focus its firepower to the Red force itself or one of its supply agents. This optimal fire allocation is derived and proved by considering an optimization problem of number of Blue force troops. Numerical experiments are included to demonstrate the theoretical results.