Human Learning Optimization (HLO) is a novel potential and promising meta-heuristic, which is developed based on a simplified human learning model. In recent years, the hypothesis that the human cognitive process obeys the laws of quantum rather than classical probability has been successfully used to explain a variety of seemingly “irrational” judgment and human decision-making behaviors, and the independent evidence for this hypothesis has been provided from different experiments. Inspired by this hypothesis, this paper introduces a quantum cognition model of humans into HLO and proposes a quantum-like human learning optimization algorithm (QHLO), in which the belief and its change in human brains during the learning process is simulated and implemented in the search of the algorithm. The developed QHLO is validated on the benchmark functions, and the performance is compared with one recent HLO variants, two quantum-inspired meta-heuristics and two recent binary meta-heuristics. The experimental results show that that the presented QHLO inherits the advantages of HLO and has better global search ability as its diversity is further enhanced with the integration of the quantum cognition model.