Diversifying behaviors for learning in asymmetric multiagent systems

Diversifying behaviors for learning in asymmetric multiagent systems
复制标题

非对称多智能体系统中学习行为的多样化

DOI:
10.1145/3512290.3528860
复制
发表时间:
2022
期刊:
Genetic and Evolutionary Computation Conference
影响因子:
--
通讯作者:
Tumer, Kagan
Tumer, Kagan
中科院分区:
--
文献类型:
--
作者:
Dixit, Gaurav;Gonzalez, Everardo;Tumer, Kagan

文献摘要

参考文献

相似文献

为了在多智能体系统(如空中交通管制或搜索和救援)中实现协调,智能体不仅要进化自己的策略,还要适应其他智能体的行为。然而,扩展协同进化算法的复杂领域是困难的,因为代理演变的动态环境中所创建的其他代理的不断变化的政策。当团队由不同的非对称代理(具有不同能力和目标的代理)组成时,这个问题会加剧,这使得代理很难制定互补的政策。质量多样性方法通过允许代理发现不仅是最佳的,而且是不同的行为,但在多代理设置中计算上是棘手的,从而解决了部分问题。本文介绍了一个多智能体学习框架,让非对称代理专门和探索不同的行为需要在共享的环境中进行协调。这项工作的关键见解是,多样性搜索,适应度优化和团队组成建模的层次分解,允许团队范围内的目标,以指导多样性搜索在动态环境中的适应度。多智能体环境中的时间和空间耦合的要求的实验结果表明,收购代理协同作用的多样性,以应对不断变化的环境和团队组成。
To achieve coordination in multiagent systems such as air traffic control or search and rescue, agents must not only evolve their policies, but also adapt to the behaviors of other agents. However, extending coevolutionary algorithms to complex domains is difficult because agents evolve in the dynamic environment created by the changing policies of other agents. This problem is exacerbated when the teams consist of diverse asymmetric agents (agents with different capabilities and objectives), making it difficult for agents to evolve complementary policies. Quality-Diversity methods solve part of the problem by allowing agents to discover not just optimal, but diverse behaviors, but are computationally intractable in multiagent settings. This paper introduces a multiagent learning framework to allow asymmetric agents to specialize and explore diverse behaviors needed for coordination in a shared environment. The key insight of this work is that a hierarchical decomposition of diversity search, fitness optimization, and team composition modeling allows the fitness on the team-wide objective to direct the diversity search in a dynamic environment. Experimental results in multiagent environments with temporal and spatial coupling requirements demonstrate the diversity of acquired agent synergies in response to a changing environment and team compositions.
DOI: --
发表时间: 2019-01
期刊: ArXiv
影响因子: --
作者:
Rui Wang;J. Lehman;J. Clune;Kenneth O. Stanley
通讯作者: Rui Wang;J. Lehman;J. Clune;Kenneth O. Stanley
分布式空中交通管制的多代理系统架构
DOI: --
发表时间: 2005
期刊:
影响因子: --
作者:
J. Hill;J. Archibald;W. Stirling;R. Frost
通讯作者: R. Frost
通过资源限制实现最小标准协同进化的多样性保护
DOI: --
发表时间: 2020
期刊: Annual Conference on Genetic and Evolutionary Computation
影响因子: --
作者:
Jonathan C. Brant;Kenneth O. Stanley
通讯作者: Kenneth O. Stanley
结合 MAP-Elite 和增量进化来生成哺乳动物四足机器人的步态
DOI: 10.1007/978-3-319-77538-8_48
发表时间: 2018
期刊: Comparative Biochemistry and Physiology Part C: Comparative Pharmacology
影响因子: --
作者:
Jørgen Nordmoen;K. Ellefsen;K. Glette
通讯作者: K. Glette