Cargando…

Making friends on the fly advances in ad hoc teamwork

This book is devoted to the encounter and interaction of agents such as robots with other agents and describes how they cooperate with their previously unknown teammates, forming an Ad Hoc team. It presents a new algorithm, PLASTIC, that allows agents to quickly adapt to new teammates by reusing kno...

Descripción completa

Detalles Bibliográficos
Autor principal: Barrett, Samuel
Lenguaje:eng
Publicado: Springer 2015
Materias:
Acceso en línea:https://dx.doi.org/10.1007/978-3-319-18069-4
http://cds.cern.ch/record/2020996
_version_ 1780946876009283584
author Barrett, Samuel
author_facet Barrett, Samuel
author_sort Barrett, Samuel
collection CERN
description This book is devoted to the encounter and interaction of agents such as robots with other agents and describes how they cooperate with their previously unknown teammates, forming an Ad Hoc team. It presents a new algorithm, PLASTIC, that allows agents to quickly adapt to new teammates by reusing knowledge learned from previous teammates.  PLASTIC is instantiated in both a model-based approach, PLASTIC-Model, and a policy-based approach, PLASTIC-Policy.  In addition to reusing knowledge learned from previous teammates, PLASTIC also allows users to provide expert-knowledge and can use transfer learning (such as the new TwoStageTransfer algorithm) to quickly create models of new teammates when it has some information about its new teammates. The effectiveness of the algorithm is demonstrated on three domains, ranging from multi-armed bandits to simulated robot soccer games.
id cern-2020996
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2015
publisher Springer
record_format invenio
spelling cern-20209962021-04-21T20:16:50Zdoi:10.1007/978-3-319-18069-4http://cds.cern.ch/record/2020996engBarrett, SamuelMaking friends on the fly advances in ad hoc teamworkEngineeringThis book is devoted to the encounter and interaction of agents such as robots with other agents and describes how they cooperate with their previously unknown teammates, forming an Ad Hoc team. It presents a new algorithm, PLASTIC, that allows agents to quickly adapt to new teammates by reusing knowledge learned from previous teammates.  PLASTIC is instantiated in both a model-based approach, PLASTIC-Model, and a policy-based approach, PLASTIC-Policy.  In addition to reusing knowledge learned from previous teammates, PLASTIC also allows users to provide expert-knowledge and can use transfer learning (such as the new TwoStageTransfer algorithm) to quickly create models of new teammates when it has some information about its new teammates. The effectiveness of the algorithm is demonstrated on three domains, ranging from multi-armed bandits to simulated robot soccer games.Springeroai:cds.cern.ch:20209962015
spellingShingle Engineering
Barrett, Samuel
Making friends on the fly advances in ad hoc teamwork
title Making friends on the fly advances in ad hoc teamwork
title_full Making friends on the fly advances in ad hoc teamwork
title_fullStr Making friends on the fly advances in ad hoc teamwork
title_full_unstemmed Making friends on the fly advances in ad hoc teamwork
title_short Making friends on the fly advances in ad hoc teamwork
title_sort making friends on the fly advances in ad hoc teamwork
topic Engineering
url https://dx.doi.org/10.1007/978-3-319-18069-4
http://cds.cern.ch/record/2020996
work_keys_str_mv AT barrettsamuel makingfriendsontheflyadvancesinadhocteamwork