Studies of dynamics of physical agent ecosystems

dc.contributor
Universitat de Girona. Departament d'Electrònica, Informàtica i Automàtica
dc.contributor.author
Muñoz Moreno, Israel
dc.date.accessioned
2011-04-12T17:35:13Z
dc.date.available
2003-01-15
dc.date.issued
2002-09-04
dc.date.submitted
2003-01-15
dc.identifier.isbn
846880973X
dc.identifier.uri
http://www.tdx.cat/TDX-0115103-140323
dc.identifier.uri
http://hdl.handle.net/10803/7717
dc.description.abstract
This thesis addresses the problem of learning in physical heterogeneous multi-agent systems<br/>(MAS) and the analysis of the benefits of using heterogeneous MAS with respect to<br/>homogeneous ones. An algorithm is developed for this task; building on a previous work on stability in distributed systems by Tad Hogg and Bernardo Huberman, and combining two phenomena observed in natural systems, task partition and hierarchical dominance. This algorithm is devised for allowing agents to learn which are the best tasks to perform on the basis of each agent's skills and the contribution to the team global performance. Agents learn by interacting with the environment and other teammates, and get rewards from the result of the actions they perform. This algorithm is specially designed for problems where all robots have to co-operate and work simultaneously towards the same goal. One example of such a problem is role distribution in a team of heterogeneous robots that form a soccer team, where all members take decisions and co-operate simultaneously. Soccer offers the possibility of conducting research in MAS, where co-operation plays a very important role in a dynamical and changing environment. For these reasons and the experience of the University of Girona in this domain, soccer has been selected as the test-bed for this research. In the case of soccer, tasks are grouped by means of roles.<br/>One of the most interesting features of this algorithm is that it endows MAS with a high<br/>adaptability to changes in the environment. It allows the team to perform their tasks, while<br/>adapting to the environment. This is studied in several cases, for changes in the environment and in the robot's body. Other features are also analysed, especially a parameter that defines the fitness (biological concept) of each agent in the system, which contributes to performance and team adaptability.<br/>The algorithm is applied later to allow agents to learn in teams of homogeneous and<br/>heterogeneous robots which roles they have to select, in order to maximise team performance. The teams are compared and the performance is evaluated in the games against three hand-coded teams and against the different homogeneous and heterogeneous teams built in this thesis. This section focuses on the analysis of performance and task partition, in order to study the benefits of heterogeneity in physical MAS.<br/>In order to study heterogeneity from a rigorous point of view, a diversity measure is developed building on the hierarchic social entropy defined by Tucker Balch. This is adapted to quantify physical diversity in robot teams. This tool presents very interesting features, as it can be used in the future to design heterogeneous teams on the basis of the knowledge on other teams.
cat
dc.format.mimetype
application/pdf
dc.language.iso
eng
dc.publisher
Universitat de Girona
dc.rights.license
ADVERTIMENT. L'accés als continguts d'aquesta tesi doctoral i la seva utilització ha de respectar els drets de la persona autora. Pot ser utilitzada per a consulta o estudi personal, així com en activitats o materials d'investigació i docència en els termes establerts a l'art. 32 del Text Refós de la Llei de Propietat Intel·lectual (RDL 1/1996). Per altres utilitzacions es requereix l'autorització prèvia i expressa de la persona autora. En qualsevol cas, en la utilització dels seus continguts caldrà indicar de forma clara el nom i cognoms de la persona autora i el títol de la tesi doctoral. No s'autoritza la seva reproducció o altres formes d'explotació efectuades amb finalitats de lucre ni la seva comunicació pública des d'un lloc aliè al servei TDX. Tampoc s'autoritza la presentació del seu contingut en una finestra o marc aliè a TDX (framing). Aquesta reserva de drets afecta tant als continguts de la tesi com als seus resums i índexs.
dc.source
TDX (Tesis Doctorals en Xarxa)
dc.subject
Multi-agent systems
dc.subject
Aprenentatge
dc.subject
Sistemes multiagent
dc.subject
Learning
dc.subject
Robots
dc.subject
Sistemas multi-agente
dc.subject
Aprendizaje
dc.title
Studies of dynamics of physical agent ecosystems
dc.type
info:eu-repo/semantics/doctoralThesis
dc.type
info:eu-repo/semantics/publishedVersion
dc.subject.udc
004
cat
dc.contributor.authoremail
imunoz@silver.udg.es
dc.contributor.director
Rosa, Josep Lluís de la
dc.rights.accessLevel
info:eu-repo/semantics/openAccess
cat
dc.identifier.dl
Gi. 424-2002


Documentos

timn.pdf

754.4Kb PDF

Este ítem aparece en la(s) siguiente(s) colección(ones)