Processing

Please wait...

Settings

Settings

Goto Application

1. US20200302322 - MACHINE LEARNING SYSTEM

Office United States of America
Application Number 16753580
Application Date 04.10.2018
Publication Number 20200302322
Publication Date 24.09.2020
Publication Kind A1
IPC
G06N 7/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
7Computer systems based on specific mathematical models
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 3/00
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
CPC
G06N 3/006
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
004Artificial life, i.e. computers simulating life
006based on simulated virtual individual or collective life forms, e.g. single "avatar", social simulations, virtual worlds or particle swarm optimisation
G06N 7/005
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
7Computer systems based on specific mathematical models
005Probabilistic networks
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
Applicants PROWLER ,IO LIMITED
Inventors Aleksi TUKIAINEN
Dongho KIM
Thomas NICHOLSON
Marcin TOMCZAK
Jose Enrique MUNOZ DE COTE FLORES LUNA
Neil FERGUSON
Stefanos ELEFTHERIADIS
Juha SEPPA
David BEATTIE
Joel JENNINGS
James HENSMAN
Felix LEIBFRIED
Jordi GRAU-MOYA
Sebastian JOHN
Peter VRANCX
Haitham BOU AMMAR
Priority Data 17275185 21.11.2017 EP
20170100448 04.10.2017 GR
Title
(EN) MACHINE LEARNING SYSTEM
Abstract
(EN)

There is described a machine learning system comprising a first subsystem and a second subsystem remote from the first subsystem. The first subsystem comprises an environment having multiple possible states and a decision making subsystem comprising one or more agents. Each agent is arranged to receive state information indicative of a current state of the environment and to generate an action signal dependent on the received state information and a policy associated with that agent, the action signal being operable to cause a change in a state of the environment. Each agent is further arranged to generate experience data dependent on the received state information and information conveyed by the action signal. The first subsystem includes a first network interface configured to send said experience data to the second subsystem and to receive policy data from the second subsystem. The second subsystem comprises: a second network interface configured to receive experience data from the first subsystem and send policy data to the first subsystem; and a policy learner configured to process said received experience data to generate said policy data, dependent on the experience data, for updating one or more policies associated with the one or more agents. The decision making subsystem is operable to update the one or more policies associated with the one or more agents in accordance with policy data received from the second subsystem.

Also published as