Identifying Coordination in a Cognitive Radar Network -- A Multi-Objective Inverse Reinforcement Learning Approach

TL;DR

This paper introduces a novel multi-objective inverse reinforcement learning method to detect and reconstruct coordination among radars in a cognitive network, based on observed emissions and Pareto optimality.

Contribution

It presents a new approach combining inverse reinforcement learning and micro-economic revealed preferences to identify and analyze multi-objective coordination in radar networks.

Findings

Successfully detects Pareto optimal coordination behavior.

Reconstructs individual radar utility functions from emission data.

Applicable to general inverse detection of multi-objective systems.

Abstract

Consider a target being tracked by a cognitive radar network. If the target can intercept some radar network emissions, how can it detect coordination among the radars? By 'coordination' we mean that the radar emissions satisfy Pareto optimality with respect to multi-objective optimization over each radar's utility. This paper provides a novel multi-objective inverse reinforcement learning approach which allows for both detection of such Pareto optimal ('coordinating') behavior and subsequent reconstruction of each radar's utility function, given a finite dataset of radar network emissions. The method for accomplishing this is derived from the micro-economic setting of Revealed Preferences, and also applies to more general problems of inverse detection and learning of multi-objective optimizing systems.