Model-Free Online Learning for Waveform Optimization In Integrated Sensing And Communications

This paper considers waveform optimization problems for managing and mitigating interference in integrated sensing and communications (ISAC) systems. In particular, we consider dynamic shared spectrum scenarios where channel and interference statistics are nonstationary. The focus is on allocating frequency and power resources in multicarrier ISAC systems. A data-efficient Model-Free Online Learning (MFOL) algorithm is proposed as an alternative to the previously proposed Model-Based Online Learning (MBOL) approach. Empirical results show that the MFOL method learns slower than the MBOL method but can perform better when a large number of training samples are available.