Adaptive Parameter Selection in Evolutionary Algorithms by Reinforcement Learning with Dynamic Discretization of Parameter Range

2016-03-22 · Arkady Rost, Irina Petrova, Arina Buzdalova

Online parameter controllers for evolutionary algorithms adjust values of parameters during the run of an evolutionary algorithm. Recently a new efficient parameter controller based on reinforcement learning was proposed by Karafotias et al. In this method ranges of parameters are discretized into several intervals before the run. However, performing adaptive discretization during the run may increase efficiency of an evolutionary algorithm. Aleti et al. proposed another efficient controller with adaptive discretization. In the present paper we propose a parameter controller based on reinforcement learning with adaptive discretization. The proposed controller is compared with the existing parameter adjusting methods on several test problems using different configurations of an evolutionary algorithm. For the test problems, we consider four continuous functions, namely the sphere function, the Rosenbrock function, the Levi function and the Rastrigin function. Results show that the new controller outperforms the other controllers on most of the considered test problems.

📄 PDF Abstract BibTeX arXiv:1603.06788

Code (0)

등록된 구현이 없습니다.

Tasks

Evolutionary Algorithmsreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Java Implementation of a Parameter-less Evolutionary Portfolio

2015-06-26 · José C. Pereira, Fernando G. Lobo

The Java implementation of a portfolio of parameter-less evolutionary algorithms is presented. The Parameter-less Evolutionary Portfolio implements a heuristic that performs adaptive selection of parameter-less evolution…

Bayesian Optimization Evolutionary Algorithms

Deep Reinforcement Learning Based Parameter Control in Differential Evolution

2019-05-20 · Mudita Sharma, Alexandros Komninos, Manuel Lopez Ibanez, Dimitar Kazakov

Adaptive Operator Selection (AOS) is an approach that controls discrete parameters of an Evolutionary Algorithm (EA) during the run. In this paper, we propose an AOS method based on Double Deep Q-Learning (DDQN), a Deep …

Deep Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1

Constrained Multi-objective Optimization with Deep Reinforcement Learning Assisted Operator Selection

2024-01-15 · Fei Ming, Wenyin Gong, Ling Wang, Yaochu Jin

Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable attention. Various constrained multi-objective optimization evolutionary algorithms (CMOEAs) have been dev…

Deep Reinforcement Learning Evolutionary Algorithms reinforcement-learning Reinforcement Learning

Effective Mutation Rate Adaptation through Group Elite Selection

2022-04-11 · Akarsh Kumar, Bo Liu, Risto Miikkulainen, Peter Stone

Evolutionary algorithms are sensitive to the mutation rate (MR); no single value of this parameter works well across domains. Self-adaptive MR approaches have been proposed but they tend to be brittle: Sometimes they dec…

Evolutionary Algorithms image-classification Image Classification

Evolutionary Action Selection for Gradient-based Policy Learning

2022-01-12 · Yan Ma, Tianxing Liu, Bingsheng Wei, Yi Liu 외

Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation.The evolutionary part in these hybrid me…

continuous-control Continuous Control Deep Reinforcement Learning Evolutionary Algorithms