Adaptive ECCM for Mitigating Smart Jammers

A list of standard ECM and ECCM strategies are summarized in [1] and [2]. This paper considers adaptive radar electronic counter-counter This paper formulates the radar's ECCM objective as a measures (ECCM) to mitigate ECM by an adversarial jammer. Principle Agent Problem (PAP), wherein the radar gradually Our ECCM approach models the jammer-radar interaction learns the jammer's objective using Inverse Reinforcement as a Principal Agent Problem (PAP), a popular economics Learning (IRL). We assume the radar possesses IRL capability framework for interaction between two entities with and can learn the jammer's utility, while the jammer an information imbalance. In our setup, the radar does not is a naive agent - it only maximizes its utility. Reconstructing know the jammer's utility. Instead, the radar learns the jammer's agent preferences from a finite time series dataset is the utility adaptively over time using inverse reinforcement central theme of revealed preference in micro-economics [3], learning. The radar's adaptive ECCM objective is two-fold [4]. In the radar context, the radar uses the celebrated result (1) maximize its utility by solving the PAP, and (2) estimate of Afriat's theorem [3] to estimate the jammer's utility over the jammer's utility by observing its response.