arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.04751cs.AI
收藏

DeepHive:一种用于自动发现群体优化策略的多智能体强化学习方法

DeepHive: A multi-agent reinforcement learning approach for automated discovery of swarm-based optimization policies

Louisiana State University(路易斯安那州立大学)

Eloghosa Ikponmwoba, Ope Owoyele

AI总结:

本文提出DeepHive,将群体优化器设计建模为多智能体强化学习问题,以少量函数评估实现黑箱全局优化,实验证明其性能优于现有优化器并具备良好扩展性与泛化能力。

摘要:

我们提出了一种用于设计基于群体的优化器的方法,以解决昂贵黑箱函数的全局优化问题。在所提出的方法中,寻找高效优化器的问题被构建为一个强化学习问题,其目标是找到只需少量函数评估即可收敛到全局最优的优化策略。群体中每个智能体的状态被定义为其在设计空间中的当前位置和函数值,智能体学习采取有利的动作以最大化奖励,该奖励基于目标函数的最终值。所提出的方法在多个基准优化函数上进行了测试,并与其他全局优化策略的性能进行了比较。此外,还研究了改变智能体数量的影响以及训练后智能体的泛化能力。结果表明,与其他优化器相比,该方法具有优越的性能,在智能体数量变化时表现出理想的扩展性,并且即使应用于未见过的函数也能获得可接受的性能。从更广泛的层面来看,这些结果为快速开发特定领域的优化器展现了前景。

英文摘要:

We present an approach for designing swarm-based optimizers for the global optimization of expensive black-box functions. In the proposed approach, the problem of finding efficient optimizers is framed as a reinforcement learning problem, where the goal is to find optimization policies that require a few function evaluations to converge to the global optimum. The state of each agent within the swarm is defined as its current position and function value within a design space and the agents learn to take favorable actions that maximize reward, which is based on the final value of the objective function. The proposed approach is tested on various benchmark optimization functions and compared to the performance of other global optimization strategies. Furthermore, the effect of changing the number of agents, as well as the generalization capabilities of the trained agents are investigated. The results show superior performance compared to the other optimizers, desired scaling when the number of agents is varied, and acceptable performance even when applied to unseen functions. On a broader scale, the results show promise for the rapid development of domain-specific optimizers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑