Proximal Policy Optimization-Based Transmit Beamforming and Phase-Shift Design in an IRS-Aided ISAC System for the THz Band

In this paper, an IRS-aided integrated sensing and communications (ISAC) system operating in the terahertz (THz) band is proposed to maximize capacity. Transmit beamforming phase-shift design are transformed into a universal optimization problem with ergodic constraints. Then joint of transmit achieved by gradient-based, primal-dual proximal policy (PPO) multi-user multiple-input single-output (MISO) scenario. Specifically, actor part generates continuous critic takes charge discrete phase shift design. Based on MISO scenario, we investigate distributed PPO (DPPO) framework concept multi-threading learning multiple-output (MIMO) Simulation results demonstrate effectiveness algorithm its version terms