公开(公告)号：WO0045584A8

公开(公告)日：2000-11-02

申请号：PCT/US0002011

申请日：2000-01-28

Applicant: BIOS GROUP LP ,  KAUFFMAN STUART A ,  PLATE TONY A

Inventor： KAUFFMAN STUART A ,  PLATE TONY A

IPC: H04L12/701 ,  H04L12/721 ,  H04L12/725 ,  H04M15/00 ,  G06F15/18 ,  H04L12/46

CPC classification number: H04L45/12 ,  H04L45/00 ,  H04L45/308

Abstract: The present invention relates generally to a method and system for routing control in communication networks and for system control. More particularly, the present invention performs routing by controlling the components in a network with software agents (102) operating in a reward framework using p, tau, and patches (104) to improve communication performance (106). This invention disclosure includes the combination of reinforcement learning agents in a market-based or performance-based reward framework together with optimization techniques called p, tau, and patches (104) as applied to the problem of topology-and load-based routing in data networks, in order to improve communication performance (106) such as communication latency and bandwidth. The invention also applies to the control of other systems, including operations management, job-shop problems, organizational structure, portfolio management, risk management etc.

Abstract translation: 本发明一般涉及用于通信网络中的路由控制和系统控制的方法和系统。 更具体地说，本发明通过使用p，tau和补丁（104）在奖励框架中运行的软件代理（102）控制网络中的组件来执行路由，以改善通信性能（106）。 本发明公开内容包括基于市场或基于性能的奖励框架中的强化学习代理的组合以及被应用于数据中的基于拓扑和基于负载的路由问题的被称为p，tau和补丁（104）的优化技术 网络，以便改善诸如通信等待时间和带宽的通信性能（106）。 本发明也适用于其他系统的控制，包括运营管理，作业问题，组织结构，投资组合管理，风险管理等。

公开(公告)号：AU2860600A

公开(公告)日：2000-08-18

申请号：AU2860600

申请日：2000-01-28

Applicant: BIOS GROUP LP

Inventor： KAUFFMAN STUART A ,  PLATE TONY A

IPC: H04L12/701 ,  H04L12/721 ,  H04L12/725 ,  H04M15/00 ,  G06F15/18 ,  H04L12/46