Optimizing time-dependent multi-agile Earth observation satellite scheduling problem using deep Q-learning and ensemble heuristics
Abstract: Highlights•The two-stage method TAM-ECH is proposed for solving the MAEOSSP.•TAM ensures efficiently allocating tasks to each single satellite through DRL.•ECH employs ensemble heuristics for fast and stable single-satellite scheduling.•Comprehensive experiments have validated the effectiveness of each component.
Loading