.png){kind=icon}
返回
A framework for co-evolutionary algorithm using Q-learning with meme
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2023.120186.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A large number of metaheuristic algorithms have been proposed in the last three decades, but no metaheuristic algorithm is superior to the others for all the optimization problems. It is laborious to select an appropriate metaheuristic algorithm to solve a problem, especially for laymen. In this paper, a framework for co-evolutionary algorithm using Q-learning with the meme is proposed, which is called as QLMA. The solution generation method in the metaheuristic algorithm is named meme, which is also viewed as the action for an agent in Q-learning, and multiple memes form the action set. In the initial stage, the tent map and opposition based learning are employed to obtain the initial population. In updating stage, a new population is generated by an action that is chosen from the action set by the agent in Q-learning, then the disruption operation is applied, avoiding excessive aggregation of solutions around the current global optimal solution and improving the balance between exploration and exploitation. QLMA is compared to sixteen algorithms on 23 classical benchmark functions, CEC 2017, and CEC 2019 benchmark functions. The experimental results demonstrate that QLMA is superior to the peer algorithms and has a good balance between exploration and exploitation.
Keyword:
Metaheuristic algorithm
Q-learning
Chaos
Opposition based learning
Disruption
期刊
IF:
7.5
论文数:
3.0W
被引数:
11.4W
机构
引用论文
.png){kind=icon}
Particle swarm optimisation in designing parameters of manufacturing processes: A review (2008-2018)
PREAI
分享收藏
Chameleon Swarm Algorithm: A bio-inspired optimizer for solving engineering design problems变色龙群算法: 解决工程设计问题的生物启发优化器
PREAI
分享收藏分享收藏
An adaptive artificial bee colony with reinforcement learning for distributed three-stage assembly scheduling with maintenance具有强化学习的自适应人工蜂群算法，用于具有维护功能的分布式三阶段装配调度
PREAI
分享收藏
查看更多内容