Education, Science, Technology, Innovation and Life
Open Access
Sign In

A Comparative Review of Reinforcement Learning and Traditional Algorithms in Typical Optimization Problems

Download as PDF

DOI: 10.23977/jaip.2026.090104 | Downloads: 0 | Views: 39

Author(s)

Suyang Wu 1

Affiliation(s)

1 School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, China

Corresponding Author

Suyang Wu

ABSTRACT

Combinatorial optimization problems are widely present in fields such as logistics scheduling and manufacturing, among which the Traveling Salesman Problem (TSP) and Job Shop Scheduling Problem (JSSP) are two highly representative basic problems. As an emerging intelligent optimization method, reinforcement learning (RL) exhibits potential advantages in solving optimization problems due to its characteristic of learning through interaction with the environment; while traditional optimization algorithms such as greedy algorithms and genetic algorithms have formed mature solution frameworks after long-term development. Taking TSP and JSSP as research carriers, this paper systematically sorts out the differences in solution mechanisms and performance between reinforcement learning, greedy algorithms, and genetic algorithms from two core dimensions: solution speed and optimal solution quality. It analyzes the applicable scenarios of various algorithms in combination with existing research results, providing references for algorithm selection in optimization problems. Finally, the shortcomings of current research are summarized, and future research directions are prospected.

KEYWORDS

Reinforcement Learning; Greedy Algorithm; Genetic Algorithm; Traveling Salesman Problem; Job Shop Scheduling; Optimization Comparison

CITE THIS PAPER

Suyang Wu. A Comparative Review of Reinforcement Learning and Traditional Algorithms in Typical Optimization Problems. Journal of Artificial Intelligence Practice (2026) Vol. 9: 27-32. DOI: http://dx.doi.org/10.23977/jaip.2026.090104.

REFERENCES

[1] Graves, Alex, et al. "Hybrid computing using a neural network with dynamic external memory." Nature 538.7626 (2016): 471-476.
[2] Jain, Vinod, and Jay Shankar Prasad. "Solving travelling salesman problem using greedy genetic algorithm GGA." Int. J. Eng. Technol 9.2 (2017): 1148-1154.
[3] Yang, Yunhao, and Andrew Whinston. "A survey on reinforcement learning for combinatorial optimization." 2023 IEEE World Conference on Applied Intelligence and Computing (AIC). IEEE, 2023.
[4] Barrett, Thomas, et al. "Exploratory combinatorial optimization with reinforcement learning." Proceedings of the AAAI conference on artificial intelligence. Vol. 34. No. 04. 2020.

Downloads: 17511
Visits: 652370

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.