Distributionally Robust Inverse Reinforcement Learning for Identifying Multi-Agent Coordinated Sensing

2024/09/22 by Luke Snow, Vikram Krishnamurthy, Snow, Luke +1
Computer Science · #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2409.14542

openalex publication_date 2024/09/22 · openalex created_date 2024/10/26 · openalex updated_date 2026/07/28

Abstract

We derive a minimax distributionally robust inverse reinforcement learning (IRL) algorithm to reconstruct the utility functions of a multi-agent sensing system. Specifically, we construct utility estimators which minimize the worst-case prediction error over a Wasserstein ambiguity set centered at noisy signal observations. We prove the equivalence between this robust estimation and a semi-infinite optimization reformulation, and we propose a consistent algorithm to compute solutions. We illustrate the efficacy of this robust IRL scheme in numerical studies to reconstruct the utility functions of a cognitive radar network from observed tracking signals.

Related

• Multi-Agent Inverse Reinforcement Learning for Identifying Pareto-Efficient Coordination -- A Distributionally Robust Approach
• Identifying Coordination in a Cognitive Radar Network -- A Multi-Objective Inverse Reinforcement Learning Approach
• Adversarial Radar Inference. From Inverse Tracking to Inverse\n Reinforcement Learning of Cognitive Radar
• Inverse-Inverse Reinforcement Learning. How to Hide Strategy from an Adversarial Inverse Reinforcement Learner
• Signal attenuation enables scalable decentralized multi-agent reinforcement learning over networks