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
Online AccessGet full text

Cover

Loading…
Abstract 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.
AbstractList 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.
Author DEVLIN, Sam Michael
SLOWEY, Andrew Philip
NANAVATI, Jay
DIGGLE, Anthony David Joseph
AGRAWAL, Janhavi
BIGNELL, David Michael
O'GRADY, Adrian Kieron
HOFMANN, Katja
Author_xml – fullname: SLOWEY, Andrew Philip
– fullname: HOFMANN, Katja
– fullname: NANAVATI, Jay
– fullname: AGRAWAL, Janhavi
– fullname: BIGNELL, David Michael
– fullname: DIGGLE, Anthony David Joseph
– fullname: DEVLIN, Sam Michael
– fullname: O'GRADY, Adrian Kieron
BookMark eNrjYmDJy89L5WSQDQly9PTz9HNXcHL1cAzz9A9S8HdTcPRTcHR39QvhYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkYGxqZmFpbmjobGxKkCANh2I4k
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US2020356897A1
GroupedDBID EVB
ID FETCH-epo_espacenet_US2020356897A13
IEDL.DBID EVB
IngestDate Fri Jul 19 14:50:26 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US2020356897A13
Notes Application Number: US201916508287
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201112&DB=EPODOC&CC=US&NR=2020356897A1
ParticipantIDs epo_espacenet_US2020356897A1
PublicationCentury 2000
PublicationDate 20201112
PublicationDateYYYYMMDD 2020-11-12
PublicationDate_xml – month: 11
  year: 2020
  text: 20201112
  day: 12
PublicationDecade 2020
PublicationYear 2020
RelatedCompanies Microsoft Technology Licensing, LLC
RelatedCompanies_xml – name: Microsoft Technology Licensing, LLC
Score 3.2957761
Snippet 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...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Title TRAINING BEHAVIOR OF AN AGENT
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201112&DB=EPODOC&locale=&CC=US&NR=2020356897A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED_G_HzTqkzdpKD0rWiadlsfivRzrbB2dO3Y21jTBgSZw1b8901Cp3vaY-7g8sXl7pfcXQCekEnxuMS6WiKyVnWt0lWzNAx1jRHBJdtxLLLSpvEwzPW3pbHswMcuF0bUCf0RxRGZRhGm7404r7f_l1ieiK2sn4t3Rvp8DTLLU1p0zK0Z0hTPsfxZ4iWu4rpWPlfiVPCwMRybI5thpSPuSPNK-_7C4Xkp232jElzA8YzJ2zSX0Kk2Epy5u7_XJDidtk_eEpyIGE1SM2Krh_UVDLLUjuIonsiOH9qLKEnlJJDtWLYnfpxdw2PgZ26osh5XfxNc5fP94eEb6DLoX_VARoTQNaIjg3Icp70UiHlMlDBMgAqDFuYt9A9JujvMvodz3uSZdUjrQ7f5-q4GzMQ2xYNYmV-Kv3oY
link.rule.ids 230,309,786,891,25594,76906
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LT8JAEJ4QfOBNq8YHaBNNb41ut6X00JjSB63ClkAh3Bq6bRMTg0Rq_Pvubopy4jqT7DOzM9_ufLMAj8gqcS_HupojulR1rdBVKzcMdYkRxTnbcSxYaSPSDWf668JYNOBjy4URdUJ_RHFEZlGU2Xslzuv1_yWWJ3IrN0_ZOxN9vgSJ7Sk1OubeDGmK17f9cezFruK69myqkInQYaPbs0yHYaUDk9fn5cHTvM95KetdpxKcwuGYtbeqzqBRrCRoudu_1yQ4HtVP3hIciRxNumHC2g4359BJJk5EIjKQ-37ozKN4IseB7BDZGfgkuYCHwE_cUGU9pn8TTGfT3eHhS2gy6F9cgYwoLZeoNI2S4zjtOUMsYiopwwQoM8rMuob2vpZu9qvvoRUmo2E6jMjbLZxwFWfZIa0Nzerru-gwd1tld2KVfgFo8H0F
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=TRAINING+BEHAVIOR+OF+AN+AGENT&rft.inventor=SLOWEY%2C+Andrew+Philip&rft.inventor=HOFMANN%2C+Katja&rft.inventor=NANAVATI%2C+Jay&rft.inventor=AGRAWAL%2C+Janhavi&rft.inventor=BIGNELL%2C+David+Michael&rft.inventor=DIGGLE%2C+Anthony+David+Joseph&rft.inventor=DEVLIN%2C+Sam+Michael&rft.inventor=O%27GRADY%2C+Adrian+Kieron&rft.date=2020-11-12&rft.externalDBID=A1&rft.externalDocID=US2020356897A1