Soft Actor-Critic Approach to Self-Adaptive Particle Swarm Optimisation

Particle swarm optimisation (PSO) is a swarm intelligence algorithm that finds candidate solutions by iteratively updating the positions of particles in a swarm. The decentralised optimisation methodology of PSO is ideally suited to problems with multiple local minima and deceptive fitness landscape...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniel von Eschwege, Andries Engelbrecht
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/22/3481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846153105106796544
author Daniel von Eschwege
Andries Engelbrecht
author_facet Daniel von Eschwege
Andries Engelbrecht
author_sort Daniel von Eschwege
collection DOAJ
description Particle swarm optimisation (PSO) is a swarm intelligence algorithm that finds candidate solutions by iteratively updating the positions of particles in a swarm. The decentralised optimisation methodology of PSO is ideally suited to problems with multiple local minima and deceptive fitness landscapes, where traditional gradient-based algorithms fail. PSO performance depends on the use of a suitable control parameter (CP) configuration, which governs the trade-off between exploration and exploitation in the swarm. CPs that ensure good performance are problem-dependent. Unfortunately, CPs tuning is computationally expensive and inefficient. Self-adaptive particle swarm optimisation (SAPSO) algorithms aim to adaptively adjust CPs during the optimisation process to improve performance, ideally while reducing the number of performance-sensitive parameters. This paper proposes a reinforcement learning (RL) approach to SAPSO by utilising a velocity-clamped soft actor-critic (SAC) that autonomously adapts the PSO CPs. The proposed SAC-SAPSO obtains a 50% to 80% improvement in solution quality compared to various baselines, has either one or zero runtime parameters, is time-invariant, and does not result in divergent particles.
format Article
id doaj-art-d976a010a3d74f0587790990e67a1da2
institution Kabale University
issn 2227-7390
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-d976a010a3d74f0587790990e67a1da22024-11-26T18:11:34ZengMDPI AGMathematics2227-73902024-11-011222348110.3390/math12223481Soft Actor-Critic Approach to Self-Adaptive Particle Swarm OptimisationDaniel von Eschwege0Andries Engelbrecht1Department of Industrial Engineering, Stellenbosch University, Stellenbosch 7600, South AfricaDepartment of Industrial Engineering, Stellenbosch University, Stellenbosch 7600, South AfricaParticle swarm optimisation (PSO) is a swarm intelligence algorithm that finds candidate solutions by iteratively updating the positions of particles in a swarm. The decentralised optimisation methodology of PSO is ideally suited to problems with multiple local minima and deceptive fitness landscapes, where traditional gradient-based algorithms fail. PSO performance depends on the use of a suitable control parameter (CP) configuration, which governs the trade-off between exploration and exploitation in the swarm. CPs that ensure good performance are problem-dependent. Unfortunately, CPs tuning is computationally expensive and inefficient. Self-adaptive particle swarm optimisation (SAPSO) algorithms aim to adaptively adjust CPs during the optimisation process to improve performance, ideally while reducing the number of performance-sensitive parameters. This paper proposes a reinforcement learning (RL) approach to SAPSO by utilising a velocity-clamped soft actor-critic (SAC) that autonomously adapts the PSO CPs. The proposed SAC-SAPSO obtains a 50% to 80% improvement in solution quality compared to various baselines, has either one or zero runtime parameters, is time-invariant, and does not result in divergent particles.https://www.mdpi.com/2227-7390/12/22/3481particle swarm optimisationreinforcement learningsoft actor-criticself-adaptiveswarm intelligence
spellingShingle Daniel von Eschwege
Andries Engelbrecht
Soft Actor-Critic Approach to Self-Adaptive Particle Swarm Optimisation
Mathematics
particle swarm optimisation
reinforcement learning
soft actor-critic
self-adaptive
swarm intelligence
title Soft Actor-Critic Approach to Self-Adaptive Particle Swarm Optimisation
title_full Soft Actor-Critic Approach to Self-Adaptive Particle Swarm Optimisation
title_fullStr Soft Actor-Critic Approach to Self-Adaptive Particle Swarm Optimisation
title_full_unstemmed Soft Actor-Critic Approach to Self-Adaptive Particle Swarm Optimisation
title_short Soft Actor-Critic Approach to Self-Adaptive Particle Swarm Optimisation
title_sort soft actor critic approach to self adaptive particle swarm optimisation
topic particle swarm optimisation
reinforcement learning
soft actor-critic
self-adaptive
swarm intelligence
url https://www.mdpi.com/2227-7390/12/22/3481
work_keys_str_mv AT danielvoneschwege softactorcriticapproachtoselfadaptiveparticleswarmoptimisation
AT andriesengelbrecht softactorcriticapproachtoselfadaptiveparticleswarmoptimisation