Multi-Objective Optimization for Human Resource Allocation Using Reinforcement Learning and Enhanced Cuckoo Search Algorithm

In today's fiercely competitive business environment, enterprises are increasingly relying on efficient human resource allocation to improve operational efficiency and reduce operating costs. To better allocate human resources, this study proposes a multi-objective imperialist competition algorithm that integrates optimized Cuckoo Search algorithm and reinforcement learning, and creates a new human resource allocation optimization model. The new model can effectively explore solution space and adapt to talent allocation under different conditions by simulating the parasitic behavior of cuckoos and competition between empires. The results indicated that the new model performed the best when the population size was 50, the number of ruling countries was 40, the task exchange probability was 0.1, the resource replacement probability was 0.05, the colonial power coefficient was 0.2, and the number of colonies was 2. The average ideal distance of the mixed integer non-derivative optimization algorithm was 0.71, the diffusion of non-dominated solutions was 0.73, the momentum volume was 0.77, and the average response time of the solution was 2.43s. The indicators corresponding to the new model were 0.69, 0.76, 0.78, and 0.51s, respectively. Compared with the mixed integer non-derivative optimization algorithm, the new model reduced the average ideal distance by 0.02 and improved the diffusion of non-dominated solutions by 0.03. In addition, the momentum volume increased by 0.01, the average response time for solving was 0.51s, and the speed increased by 1.92s, all of which were better than the comparative algorithms. The average score of the new model after allocating human resources was above 9. The data showed that the new model had good convergence, fast solving speed, stable and high-quality results, and could effectively allocate talents. The research model has important practical significance for improving the efficiency of human resource scheduling and decision-making quality