| 27 | 0 | 2 |
| Downloads | Citas | Reads |
The graph coloring problem( GCP), a canonical NP-hard combinatorial optimization challenge, has been recognized as playing a critical role in diverse application domains such as wireless spectrum allocation, parallel task scheduling, and resource optimization. To address the computational bottlenecks posed by large-scale and structurally complex graphs, a reinforcement learning framework based on an enhanced dueling deep Q-network(DDQN) was proposed. The graph coloring process was formulated as a Markov decision process, with carefully designed state representations, action definitions, and reward functions that were used to guide the agent in minimizing color conflicts and reducing the total number of colors during training. The adopted DDQN architecture explicitly decoupled the state-value function from the action-advantage function, thereby improving policy evaluation accuracy and enhancing training stability. Extensive experiments were conducted on several standard benchmark graph datasets, and it was demonstrated that the proposed method significantly outperformed traditional heuristic algorithms in terms of solution quality, color utilization efficiency, and convergence speed. The research not only provided a scalable and generalizable intelligent optimization paradigm for the GCP but also offered a novel modeling and solution pathway for tackling complex combinatorial optimization problems via reinforcement learning.
[1]MARWANI M, KADDOUM G. Graph neural networks approach for joint wireless power control and spectrum allocation[J]. IEEE transactions on machine learning in communications and networking, 2024, 2:717-732.
[2]HOU H H, AGOS JAWADDI S N, ISMAIL A. Energy efficient task scheduling based on deep reinforcement learning in cloud environment:a specialized review[J].Future generation computer systems, 2024, 151:214-231.
[3]WU B B, GONG Y L, ZHENG H T, et al. Enterprise cloud resource optimization and management based on cloud operations[J]. Applied and computational engineering, 2024, 76(1):8-14.
[4]YAN X L, WU Z L, WU Z P, et al. Study on the network acoustics environment effects of traffic management measures by a bilevel programming model[J]. Sustainable cities and society, 2024, 101:105203.
[5]TAO X R, PAN Q K, GAO L. An iterated greedy algorithm with reinforcement learning for distributed hybrid flowshop problems with job merging[J]. IEEE transactions on evolutionary computation, 2025, 29(3):589-600.
[6]GANGADEVI E, RANI R S, DHANARAJ R K, et al.Spot-out fruit fly algorithm with simulated annealing optimized SVM for detecting tomato plant diseases[J]. Neural computing and applications, 2024, 36(8):4349-4375.
[7]ALHIJAWI B, AWAJAN A. Genetic algorithms:theory,genetic operators, solutions, and applications[J]. Evolutionary intelligence, 2024, 17(3):1245-1256.
[8]SHI D H, XU H, WANG S H, et al. Deep reinforcement learning based adaptive energy management for plug-in hybrid electric vehicle with double deep Q-network[J].Energy, 2024, 305:132402.
[9]B?UERLE N, JAS'KIEWICZ A. Markov decision processes with risk-sensitive criteria:an overview[J]. Mathematical methods of operations research, 2024, 99(1):141-178.
[10]汪建昌,王硕,李壮,等.图着色问题禁忌搜索改进算法[J].计算机科学, 2022, 49(S2):94-98.WANG J C, WANG S, LI Z, et al. Improved algorithm for tabu search of graph coloring problem[J]. Computer science, 2022, 49(S2):94-98.
[11]吕恒.解决图着色问题的膜进化算法研究[D].重庆:重庆大学, 2022.LV H. Research on membrane evolutionary algorithm for graph coloring problem[D]. Chongqing:Chongqing University, 2022.
[12]郭平,郭宾.解决图着色问题的膜进化算法[J].重庆大学学报, 2023, 46(7):23-35.GUO P, GUO B. A membrane evolutionary algorithm for solving graph coloring problem[J]. Journal of Chongqing university, 2023, 46(7):23-35.
[13]ZHOU Y M, DUVAL B, HAO J K. Improving probability learning based local search for graph coloring[J]. Applied soft computing, 2018, 65:542-553.
[14]GOUDET O, DUVAL B, HAO J K. Population-based gradient descent weight learning for graph coloring problems[J]. Knowledge-based systems, 2021, 212:106581.
Basic Information:
DOI：10.13705/j.issn.1671-6841.2025094
China Classification Code:O157.5;TP18
Citation Information:
[1]SONG Jiahuan,WANG Xiaofeng,DING Hongsheng ,et al.Solving Graph Coloring Problems Based on Improved Deep Q-network[J].Journal of Zhengzhou University(Natural Science Edition)().DOI:10.13705/j.issn.1671-6841.2025094.
Fund Information:
国家自然科学基金项目(62062001); 宁夏自然科学基金项目(2024AAC03165)
2026-04-24
2026-04-24
2026-04-24