SYSTEM DESIGN FOR AN INTEGRATED LIFELONG MACHINE LEARNING AGENT
A method, apparatus and system for lifelong reinforcement learning include receiving features of a task, communicating the task features to a learning system, where the learning system learns or performs a task related to the features based on learning or performing similar previous tasks, determini...
Saved in:
Main Authors | , , , , , , |
---|---|
Format | Patent |
Language | English |
Published |
20.06.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | A method, apparatus and system for lifelong reinforcement learning include receiving features of a task, communicating the task features to a learning system, where the learning system learns or performs a task related to the features based on learning or performing similar previous tasks, determining from the features if the task has changed and if so, communicating the features of the changed task to the learning system, where the learning system learns or performs the changed task based on learning or performing similar previous tasks, automatically annotating feature characteristics of received features including differences between the features of the original task and the features of the changed task to enable the learning system to more efficiently learn or perform at least the changed task, and if the task has not changed, processing the task features of a current task by the learning system to learn or perform the current task. |
---|---|
AbstractList | A method, apparatus and system for lifelong reinforcement learning include receiving features of a task, communicating the task features to a learning system, where the learning system learns or performs a task related to the features based on learning or performing similar previous tasks, determining from the features if the task has changed and if so, communicating the features of the changed task to the learning system, where the learning system learns or performs the changed task based on learning or performing similar previous tasks, automatically annotating feature characteristics of received features including differences between the features of the original task and the features of the changed task to enable the learning system to more efficiently learn or perform at least the changed task, and if the task has not changed, processing the task features of a current task by the learning system to learn or perform the current task. |
Author | NADAMUNI RAGHAVAN, Aswin PIACENTINO, Michael R SUR, Indranil DANIELS, Zachary HOSTETLER, Jesse RAHMAN, Abrar DIVAKARAN, Ajay |
Author_xml | – fullname: DIVAKARAN, Ajay – fullname: PIACENTINO, Michael R – fullname: NADAMUNI RAGHAVAN, Aswin – fullname: DANIELS, Zachary – fullname: HOSTETLER, Jesse – fullname: SUR, Indranil – fullname: RAHMAN, Abrar |
BookMark | eNrjYmDJy89L5WSwD44MDnH1VXBxDfZ091Nw8w9ScPRT8PQLcXUPcgxxdVHw8XRz9fH3c1fwdXT28PRzVfBxdQzy8wQKOLq7-oXwMLCmJeYUp_JCaW4GZTfXEGcP3dSC_PjU4oLE5NS81JL40GAjAyMTIDY1tnA0NCZOFQArVCzQ |
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 | US2024202538A1 |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_US2024202538A13 |
IEDL.DBID | EVB |
IngestDate | Fri Jul 19 10:42:02 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_US2024202538A13 |
Notes | Application Number: US202318535928 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240620&DB=EPODOC&CC=US&NR=2024202538A1 |
ParticipantIDs | epo_espacenet_US2024202538A1 |
PublicationCentury | 2000 |
PublicationDate | 20240620 |
PublicationDateYYYYMMDD | 2024-06-20 |
PublicationDate_xml | – month: 06 year: 2024 text: 20240620 day: 20 |
PublicationDecade | 2020 |
PublicationYear | 2024 |
RelatedCompanies | SRI International |
RelatedCompanies_xml | – name: SRI International |
Score | 3.5442824 |
Snippet | A method, apparatus and system for lifelong reinforcement learning include receiving features of a task, communicating the task features to a learning system,... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
Title | SYSTEM DESIGN FOR AN INTEGRATED LIFELONG MACHINE LEARNING AGENT |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240620&DB=EPODOC&locale=&CC=US&NR=2024202538A1 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED_m8OtNp-LHlIDSt2Lt53wo0rVpV1mzsXYyn8bStSBIN1zFf99L2HRPe0ggFziOg7v7XXK5ADzomuE4lqWruvFsqybHaWbyUkUsMOdap8xnsgNfwuze2HydWJMGfG7ewsg-oT-yOSJaVI72Xkt_vfw_xApkbeXqkX8gafESZm6grLNjEZ50TQm6Lh0OgoGv-L47ThU2kns40Lw9zJX2EHgL6PTWFa9SltshJTyB_SFyq-pTaBRVC478zc9rLThM1hfeLTiQFZr5ColrK1ydIcB-TzOakICmccQI5nHEY0Q0t41GHnoi0o9D2h-wiCSe34sZJX3qjViMBC-iLDuH-5Bmfk9FmaZ_CpiO023xjQtoVouquASCjpbbTs454mSzg2BffIZe6Oj8nqyy5PYVtHdxut69fQPHYikKo3StDc3667u4xRBc8zupu18TuIJQ |
link.rule.ids | 230,309,786,891 |
linkProvider | European Patent Office |
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=SYSTEM+DESIGN+FOR+AN+INTEGRATED+LIFELONG+MACHINE+LEARNING+AGENT&rft.inventor=DIVAKARAN%2C+Ajay&rft.inventor=PIACENTINO%2C+Michael+R&rft.inventor=NADAMUNI+RAGHAVAN%2C+Aswin&rft.inventor=DANIELS%2C+Zachary&rft.inventor=HOSTETLER%2C+Jesse&rft.inventor=SUR%2C+Indranil&rft.inventor=RAHMAN%2C+Abrar&rft.date=2024-06-20&rft.externalDBID=A1&rft.externalDocID=US2024202538A1 |