Boosting ant colony optimization via solution prediction and machine learning

Sun, Yuan; Wang, Sheng; Shen, Yunzhuang; Li, Xiaodong; Ernst, Andreas T.; Kirley, Michael

doi:10.1016/j.cor.2022.105769

Cited by 17 publications

(8 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Runka et al [33] employed strongly typed GP to evolve the state transition rules used by the AS. In addition to the complete automated design of state transition rules, Sun et al [34] and Ye et al [11] have attempted to automate the design of heuristic information used in state transition rules.…”

Section: Existing Methods For Automated Design Of Acomentioning

confidence: 99%

“…Consequently, current researchers in ACO have begun exploring how to automate the design of ACO algorithms [33][34][35]. Simultaneously, advancements in machine learning, particularly in deep learning and reinforcement learning over the past decade, have led to significant breakthroughs in fields such as image [36] and natural language processing [37,38].…”

Section: Introductionmentioning

confidence: 99%

“…For using machine learning to aid the automatic design of state transition rules for ACO, most studies, particularly those based on neural networks, rely on predicting nodes [34] or heatmaps [11]. This approach can enhance heuristic information but requires a large amount of high-quality pre-solved solutions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Design of State Transition Rules in Ant Colony Optimization by Genetic Programming: A Comprehensive Investigation

Lin,

Mei,

Zhang

2024

Preprint

View full text Add to dashboard Cite

The automated design of Ant Colony Optimization (ACO) algorithms has become increasingly significant, particularly in addressing complex combinatorial optimization problems. Although existing methods have achieved some success, they still face limitations, particularly the high dependency on expert knowledge, pre-solved data, and challenges in interpretability. Genetic Programming (GP), as a proven technology, has shown potential in optimizing the automated design state transition rules of ACO. However, existing research on GP-ACO is insufficient, particularly in terms of experimental validation and systematic evaluation. To address these issues, this study conducts comprehensive experiments to explore several key questions: the generality of GP-ACO on homogeneously distributed maps, the impact of different ACO variants on the learning capabilities of GP-ACO, the effect of 2-opt local search on the learning capabilities of GP-ACO, the enhancement of learning capabilities through the addition of more global information, and the interpretability of GP-ACO. The findings indicate that GP-ACO exhibits robust generality; variations among ACO variants have minimal impact on learning performance; 2-opt local search can somewhat diminish the performance of GP-ACO in the Max-Min Ant System (MMAS); additional global information can significantly enhance the learning capabilities of GP-ACO; and GP-ACO has good interpretability.

show abstract

Section: Existing Methods For Automated Design Of Acomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Design of State Transition Rules in Ant Colony Optimization by Genetic Programming: A Comprehensive Investigation

Lin,

Mei,

Zhang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The ants thus fail to learn from the colony's historical experience and from previously encountered features in the environment. Sun et al [23] proposed a machine learning model to initialize the initial pheromone matrix for meta-heuristic ACO to boost its performance. Instances are solved using a generic exact solver (CPLEX) to generate a training set.…”

Section: Related Workmentioning

confidence: 99%

“…For example, [24] uses a machine learning (ML) method to predict the termination point for an unseen instance using a model trained on landscape features derived from a set of training instances. Other methods use ML to improve the initial search pheromone matrix [14,23]. More specifically, the former approach concentrates on the orienteering problem, while the latter aims to address personalized journey route planning on multimodal public transport networks.…”

Section: Introductionmentioning

confidence: 99%

Learning-Based Neural Ant Colony Optimization

Liu

Qiu

Hart

et al. 2023

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

In this paper, we propose a new ant colony optimization algorithm, called learning-based neural ant colony optimization (LN-ACO), which incorporates an "intelligent ant". This intelligent ant contains a convolutional neural network pre-trained on a large set of instances which is able to predict the selection probabilities of the set of possible choices at each step of the algorithm. The intelligent ant is capable of generating a solution based on knowledge learned during training, but also guides other 'traditional' ants in improving their choices during the search. As the search progresses, the intelligent ant is also influenced by the pheromones accumulated by the colony, leading to better solutions. The key idea is that if tasks or instances share common features either in terms of their search landscape or solutions, then information learned by solving one instance can be applied to substantially accelerate the search on another. We evaluate the proposed algorithm on two public datasets and one real-world test set in the path planning domain. The results demonstrate that LN-ACO is competitive in its search capability compared to other ACO methods, with a significant improvement in convergence speed. CCS CONCEPTS• Computing methodologies → Search methodologies.

show abstract