Multi Objective Particle Swarm Optimization Based Cooperative Agents with Automated Negotiation

Abstract

This paper investigates a new hybridization of multi-objective particle swarm optimization (MOPSO) and cooperative agents (MOPSO-CA) to handle the problem of stagnation encounters in MOPSO, which leads solutions to trap in local optima. The proposed approach involves a new distribution strategy based on the idea of having a set of a sub-population, each of which is processed by one agent. The number of the sub-population and agents are adjusted dynamically through the Pareto ranking. This method allocates a dynamic number of sub-population as required to improve diversity in the search space. Additionally, agents are used for better management for the exploitation within a sub-population, and for exploration among sub-populations. Furthermore, we investigate the automated negotiation within agents in order to share the best knowledge. To validate our approach, several benchmarks are performed. The results show that the introduced variant ensures the trade-off between the exploitation and exploration with respect to the comparative algorithms.

A novel approach of many-objective particle swarm optimization with cooperative agents based on an inverted generational distance indicator

“…Local search agents were introduced for the intensification of specific search zones while perturbation agents and crossover agents were used to diversify the search. In [12], a hybridization between MAS and MOPSO algorithm was proposed to solve multi-objective problems. A set of sub-swarms was modeled as a multi-agent system where each agent was regarded as a sub-swarm.…”

“…In this work, our previous algorithm MOPSO-CA [12] is extended for solving MaOPs. The MOPSO-CA was suggested for solving MOPs, where the leader selection and shared information are handled by the dominance operator, and the updating archive is based on crowding distance.…”

Task Allocation on Layered Multiagent Systems: When Evolutionary Many-Objective Optimization Meets Deep Q-Learning

“…On this account, the EMO algorithms have been widely applied in MASs, see e.g. [51] for the optimization of the agent decision making process, and other applications include mobile tracking [44], agents optimal path searching [27] and agent cooperation with automated negotiation [28].…”