TRAINING BEHAVIOR OF AN AGENT

An apparatus is described for training a behavior of an agent in a physical or digital environment. The apparatus comprises a memory storing the location of at least one reward token in the environment. The location has been specified by a user. At least one processor executes the agent in the envir...

Full description

Saved in:
Bibliographic Details
Main Authors SLOWEY, Andrew Philip, HOFMANN, Katja, NANAVATI, Jay, AGRAWAL, Janhavi, BIGNELL, David Michael, DIGGLE, Anthony David Joseph, DEVLIN, Sam Michael, O'GRADY, Adrian Kieron
Format Patent
LanguageEnglish
Published 12.11.2020
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:An apparatus is described for training a behavior of an agent in a physical or digital environment. The apparatus comprises a memory storing the location of at least one reward token in the environment. The location has been specified by a user. At least one processor executes the agent in the environment according to a behavior policy. The processor is configured to observe values of variables comprising: an observation of the agent, an action of the agent and any reward resulting from the reward token. The processor is configured to update the behavior policy using reinforcement learning according to the observed values.
Bibliography:Application Number: US201916508287