This paper presents a Deep Reinforcement Learning (DRL)-assisted framework for joint communication and sensing in next-generation 6G systems. A novel DRL-assisted Null Space Aware (DNSA) approach is proposed for a multi-user multiple-input single-output (MU-MISO) Integrated Sensing and Communication (ISAC) setup under practical power constraints. The proposed two-stage design employs Proximal Policy Optimization (PPO) to optimize beamforming for communication in the first stage. In the second stage, a radar sensing beam is constructed within the null space of the effective communication channel, ensuring interference-free sensing. A closed form solution for radar beamformer is derived. A dynamic power-splitting mechanism, controlled via a factor α, enables flexible trade-offs between sensing accuracy and communication throughput. Simulation results confirm that the DNSA framework achieves significant sensing gains (up to 18.6 dB) and high communication rates (up to 5.09 bps/Hz). A comparison with conventional techniques like Maximum Ratio Transmission (MRT) and Zero-Forcing (ZF) is also presented as baseline. Moreover, the learned beamforming policy adapts efficiently to spatial channel variations, and also could be easily modified for fairness based rate allocation offering intelligent resource allocation suited for 6G-enabled IoT environments. The simulation results further corroborate the effectiveness of the proposed approach.

Amplitude detection (AD) is a low-complexity nonlinear scheme for information retrieval, as it only considers the envelope of the received signal. This makes it ideal in applications with low-cost low-power devices such as the Internet of Things (IoT). We consider a basic Point-to-Point (P2P) setup and develop a unified analytical framework for the asymptotic symbol error rate (SER) performance of the maximum-likelihood (ML) decoder with$M$-ary amplitude-shift keying (ASK). The developed framework is general and can be applied for a large class of fading channels. The SER can be characterized by two parameters: the diversity order and the coding gain at a sufficiently high signal-to-noise regime. We derive closed-form expressions for the exact diversity order along with a lower and upper bound on the coding gain. We show that the diversity order is equal to$m$for Nakagami-$m$fading, whereas for the other considered models, it is equal to one. We also prove that among all possible binary modulations with equal power, the modulation with one symbol equal to zero [i.e., on–off keying (OOK)] achieves the minimum asymptotic SER. The mathematical framework developed for the P2P setup is extended for cooperative relay networks. Specifically, we consider a basic amplify-and-forward (AF) three-node relay topology that employs AD at both the relay and the destination. We analytically derive the ML decoder and study asymptotic bounds on the SER by showing that the proposed AF-AD relay setup can be transformed into an equivalent P2P-AD with respect to the ML decoder.

We derive an achievable rate region (ARR) of the zero-forcing precoder in a 2 × 2 multi-user multiple-input single-output broadcast intensity-modulation/direct-detection channel. A per-light emitting diode (LED) peak optical power constraint along with a per-LED average optical power constraint with inequality (Type-I constraint) generally considered in optical wireless communication systems is imposed for which we analytically characterize the boundary of the proposed ARR. Then, we compare this ARR with that under a per-LED peak optical power constraint along with a per-LED average power constraint with equality (Type-II constraint), which is considered in visible light communication systems for constant illumination requirement. Our analysis reveals that when the ratio (β) of the maximum allowed per-LED average optical transmit power to the per-LED peak power is less than or equal to half (β ≤1/2), the ARR under both the constraints is the same. However, Type-I constrained system is analytically shown to be more power efficient in terms of the required total average transmit optical power. When β > 1/2 , the ARR under the Type-I constraint remains constant with increasing β , whereas the ARR under the Type-II constraint shrinks.