Robust reinforcement learning algorithm based on pigeon-inspired optimization by Mingying ZHANG, Bing HUA, Yuguang ZHANG, Haidong LI, Mohong ZHENG

“…Reinforcement learning(RL) is an artificial intelligence algorithm with the advantages of clear calculation logic and easy expansion of the model.Through interacting with the environment and maximizing value functions on the premise of obtaining little or no prior information, RL can optimize the performance of strategies and effectively reduce the complexity caused by physical models .The RL algorithm based on strategy gradient has been successfully applied in many fields such as intelligent image recognition, robot control and path planning for automatic driving.However, the highly sampling-dependent characteristics of RL determine that the training process needs a large number of samples to converge, and the accuracy of decision making is easily affected by slight interference that does not match with the simulation environment.Especially when RL is applied to the control field, it is difficult to prove the stability of the algorithm because the convergence of the algorithm cannot be guaranteed.Considering that swarm intelligence algorithm can solve complex problems through group cooperation and has the characteristics of self-organization and strong stability, it is an effective way to be used for improving the stability of RL model.The pigeon-inspired optimization algorithm in swarm intelligence was combined to improve RL based on strategy gradient.A RL algorithm based on pigeon-inspired optimization was proposed to solve the strategy gradient in order to maximize long-term future rewards.Adaptive function of pigeon-inspired optimization algorithm and RL were combined to estimate the advantages and disadvantages of strategies, avoid solving into an infinite loop, and improve the stability of the algorithm.A nonlinear two-wheel inverted pendulum robot control system was selected for simulation verification.The simulation results show that the RL algorithm based on pigeon-inspired optimization can improve the robustness of the system, reduce the computational cost, and reduce the algorithm’s dependence on the sample database.…”
Get full text

Ensemble machine learning algorithm for cost-effective and timely detection of diabetes in Maiduguri, Borno State by Emmanuel Gbenga Dada, Aishatu Ibrahim Birma, Abdulkarim Abbas Gora

Get full text

A Review of Stochastic Optimization Algorithms Applied in Food Engineering by Laís Koop, Nadia Maria do Valle Ramos, Adrián Bonilla-Petriciolet, Marcos Lúcio Corazza, Fernando Augusto Pedersen Voll

“…It was observed that evolutionary methods are the most applied in solving food engineering optimization problems where the genetic algorithm and differential evolution stand out. …”
Get full text

Simulated Annealing-Based Krill Herd Algorithm for Global Optimization by Gai-Ge Wang, Lihong Guo, Amir Hossein Gandomi, Amir Hossein Alavi, Hong Duan

Get full text

Simple gravitational particle swarm algorithm for multimodal optimization problems. by Yoshikazu Yamanaka, Katsutoshi Yoshida

“…Aiming to help the decision makers even if they are non-experts in optimization algorithms, this study proposes a new and simple multimodal optimization (MMO) algorithm called the gravitational particle swarm algorithm (GPSA). …”
Get full text

Decomposition-Based Multiobjective Evolutionary Algorithm for Community Detection in Dynamic Social Networks by Jingjing Ma, Jie Liu, Wenping Ma, Maoguo Gong, Licheng Jiao

“…It employs the framework of multiobjective evolutionary algorithm based on decomposition to simultaneously optimize the modularity and normalized mutual information, which quantitatively measure the quality of the community partitions and temporal cost, respectively. …”
Get full text

Optimization of distribution networks using quantum annealing for loss reduction and voltage improvement in electrical vehicle parking management by Naser Rashnu, Babak Mozafari, Reza Sharifi

“…Traditional optimization techniques like Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) often struggle with the nonlinear, high-dimensional nature of EV-grid interaction problems. …”
Get full text

Applying Genetic Algorithm for test pattern generation process optimization by V. I. Kuraedov

Get full text

Ship’s Trajectory Planning Based on Improved Multiobjective Algorithm for Collision Avoidance by Jinxin Li, Hongbo Wang, Wei Zhao, Yuanyuan Xue

“…In this paper, the optimization of ship collision avoidance strategies is realized by both an improved multiobjective optimization algorithm NSGA-II and the ship domain under the condition of a wide sea area without any external disturbances. …”
Get full text

Design of improved JAYA algorithm for cigarette finished product logistics delivery by Jun Wen, Yewei Hu, Le Li, Zongrui Wu, Guangwei Xiao, Kai Guo, Lei Li

“…In response to these challenges, this study proposes an improved Jaya algorithm that integrates a reverse learning mechanism and a cosine similarity strategy to enhance optimization performance. …”
Get full text

A binary grasshopper optimization algorithm for solving uncapacitated facility location problem by Ahmet Babalik, Aybuke Babadag

“…The Uncapacitated Facility Location Problem (UFLP) is a real-world binary optimization problem that aims to find the number of facilities to open, minimizing the total cost of exchange between customers and facilities, as well as the opening costs of these facilities. …”
Get full text

Algorithms for big data mining of hub patent transactions based on decision trees by Zhukov Aleksandr, Pronichkin Sergey, Mihaylov Yuri, Kartsan Igor

“…Based on evolutionary computing, the optimal values of the parameters of algorithms for big data mining of hub patent transactions have been established.…”
Get full text

Path Planning of Quadrupedal Robot Based on Improved RRT-Connect Algorithm by Xiaohua Xu, Peibo Li, Jiangwu Zhou, Wenzhuo Deng

Get full text

An Improved Hybrid Genetic Algorithm with a New Local Search Procedure by Wen Wan, Jeffrey B. Birch

“…One important challenge of a hybrid genetic algorithm (HGA) (also called memetic algorithm) is the tradeoff between global and local searching (LS) as it is the case that the cost of an LS can be rather high. …”
Get full text

Insulator Defect Detection Algorithm Based on Improved YOLOv11n by Junmei Zhao, Shangxiao Miao, Rui Kang, Longkun Cao, Liping Zhang, Yifeng Ren

Get full text

AC Optimal Power Flow Problem Considering Wind Energy by an Improved Particle Swarm Optimization by Mohammad Reza Ansari, Hossein Ramzaninezhad

“…To solve the AC-OPF model, an Improved Particle Swarm Optimization (IPSO) is presented. …”
Get full text

Optimizing Locations of Primary Schools in Rural Areas of China by Yulong Chen

“…Scientific location selection of schools is an important way to optimize the allocation of educational resources, improve the efficiency of operating schools, and realize the balanced development of education, especially in rural areas. …”
Get full text

Local Outlier Detection Method Based on Improved K-means by Yu ZHOU, Hao XIA, Xuezhen YUE, Peichong WANG

“…Hence, an improved K-means clustering algorithm is proposed by introducing fast search and discovering density peak methods. …”
Get full text

Operation Optimization Strategy of Commercial Combined Electric Heating System Based on Particle Swarm Optimization Algorithm by WANG Qing, LI Congcong, WANG Pingxin, WU Qingqing, CAI Xiaoyu

“… In order to improve the energy efficiency of the electric heating system, a particle swarm optimization (PSO, Particle Swarm Optimization)-based operation optimization strategy for the direct storage combined electric heating system is proposed.A mathematical model of influencing factors inside and outside the walls of electric heating buildings is established, and the simulink toolbox in matlab is used to build the overall system under the premise of determining the quantity of electric heating.Combining demand response ideas, the objective function is to establish the minimum heating and electricity cost of the user, and different sub-modules are selected to form the control module to achieve simulation verification, and the inverse cosine method is used to update the improved particle swarm algorithm to update the learning factor to solve the set objective function.Finally, through a calculation example of electricity consumption data of an enterprise in Jinan, Shandong, comparing energy consumption and economy can be obtained: the total energy consumption throughout the day is lower than the actual energy consumption, and the electricity bill is reduced by 17.16% compared with the unoptimized time.…”
Get full text

Optimal geometrical selection of skin mesh: experimental analysis and numerical optimization by Mehdi Khayami, Aisa Rassoli, Alireza Feizkhah

“…Hyperelastic properties of healthy and meshed skin were obtained through uniaxial tensile tests, and different geometries were analyzed using Abaqus. The optimal mesh geometry was then determined using genetic algorithms in Abaqus and MATLAB. …”
Get full text