An Exploration for higher efficiency in multi objective optimisation with reinforcement learning
Year: 2025
Type: preprint
Abstract: Efficiency in optimisation and search processes remain one of the challenges, which affects the performance and use of optimisation algorithms. Use of multiple operators to move within a neighbourhood looks more promising, but an optimum or near optimum sequence of operators requires further investigation, while lots of work is done for single objective optimisation, but multi-objective cases remain more challenging. A multi-agent reinforcement learning approach looks promising to tackle this problem and offer good solutions. This work introduces an prototype work in this regard, which helps demonstrate the efficiency of using multi-agent reinforcement learning.
Source: arXiv (Cornell University)
Author: Mehmet Aydin
Institution: University of the West of England
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7108222110
Cites:
Cited by:
Related to: