Enhanced Evolutionary Multi-Objective Deep Reinforcement Learning for Reliable and Efficient Wireless Rechargeable Sensor Networks
A research paper proposes an enhanced evolutionary multi-objective deep reinforcement learning algorithm to address challenges in wireless rechargeable sensor networks (WRSNs). The algorithm aims to balance node survival rates with charging energy efficiency, which are often in conflict. It integrates an LSTM-based policy network for temporal pattern recognition and a multilayer perceptron for future state prediction, outperforming existing methods in simulations. AI