Reinforcement learning in swarms that learn

机译：大量学习强化学习

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper introduces an approach to reinforcement learning by cooperating agents using a variation of the actor critic method. This is made possible by considering behavior patterns of swarms in the context of approximation spaces. Rough set theory introduced by Zdzislaw Pawlak in 1982 provides a ground for deriving pattern-based rewards within approximation spaces. The framework provided by an approximation space makes it possible to derive pattern-based reference rewards used to estimate action preferences. Approximation spaces are used to derive action-based reference rewards at the swarm intelligence level. Two different forms of the actor critic reinforcement learning method are considered as a part of a study of learning in real-time by a swarm. The contribution of this article is the presentation of a new actor critic method defined in the context of approximation spaces. An ecosystem designed to facilitate study of reinforcement learning by swarms is briefly described. In addition, the results of ecosystem experiments for two forums of the actor critic method are given.

机译：本文介绍了一种通过使用行为评论者方法的变体来通过合作主体进行强化学习的方法。通过在近似空间的情况下考虑群体的行为模式，可以做到这一点。 Zdzislaw Pawlak在1982年提出的粗糙集理论为在近似空间内得出基于模式的奖励提供了基础。近似空间提供的框架使得可以推导出用于估计动作偏好的基于模式的参考奖励。近似空间用于在群体智能级别上得出基于动作的参考奖励。演员批评家强化学习方法的两种不同形式被视为群体实时学习研究的一部分。本文的贡献是在近似空间的上下文中定义了一种新的演员评论家方法。简要描述了旨在促进群体强化学习研究的生态系统。此外，还给出了演员批评家方法两个论坛的生态系统实验结果。

著录项

来源
《Intelligent Agent Technology, IEEE/WIC/ACM International Conference on》|2005年|P.400-406|共7页
会议地点
作者
Peters J.F.; Henry C.; Ramanna S.;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类工业技术;
关键词
learning (artificial intelligence); multi-agent systems; rough set theory; actor critic method; approximation space; cooperating agent; ecosystem; reference reward; reinforcement learning; rough set theory; swarm behavior pattern;

机译：学习（人工智能）;多智能体系统;粗糙集理论;演员批评家方法;近似空间;合作代理;生态系统;参考奖励;强化学习;粗糙集理论;群体行为模式;

相似文献

外文文献
中文文献
专利

1. The left hemisphere learns what is right: Hemispatial reward learning depends on reinforcement learning processes in the contralateral hemisphere [J] . Aberg Kristoffer Carl, Doell Kimberly Crystal, Schwartz Sophie Neuropsychologia . 2016,第Null期

机译：左半球学习对的东西：半pat回奖励学习取决于对侧半球的强化学习过程
2. The left hemisphere learns what is right: Hemispatial reward learning depends on reinforcement learning processes in the contralateral hemisphere [J] . Aberg Kristoffer Carl, Doell Kimberly Crystal, Schwartz Sophie Neuropsychologia . 2016,第Null期

机译：左半球学习什么是正确的：半缺陷奖励学习取决于对侧半球的加强学习过程
3. Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations [J] . Wendelin Bohmer, Jost Tobias Springenberg, Joschka Boedecker, Kunstliche Intelligenz . 2015,第4期

机译：控制状态表示的自主学习：一个新兴领域旨在从现实世界的传感器观察中自主学习强化学习代理的状态表示
4. Reinforcement learning in swarms that learn [C] . Peters J.F., Henry C., Ramanna S. IEEE/WIC/ACM International Conference on Intelligent Agent Technology . 2005

机译：在学习的群体中加强学习
5. Robotic Swarm Control Using Deep Reinforcement Learning Strategies Based on Mean-Field Models [D] . Kakish, Zahi. 2021

机译：基于平均场模型的深增强学习策略，机器人群控制
6. Particle Swarm Optimization with Reinforcement Learning for the Prediction of CpG Islands in the Human Genome [O] . Li-Yeh Chuang, Hsiu-Chen Huang, Ming-Cheng Lin, 2008

机译：增强学习的粒子群优化算法预测人类基因组中的CpG岛
7. Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning [O] . Linchao Zhu, Sercan Ö. Arık, Yi Yang, 2020

机译：学习转移学习：加强基于学习的自适应转移学习选择

Reinforcement learning in swarms that learn

摘要

著录项

相似文献

相关主题

期刊订阅