Back to first pageBack to first page Centre for Artificial Intelligence of UNL
Browse our site
You are here:

Publication details

Go back
Publication details
Main information
A Multi-layer Framework for Evolving and Learning Agents
July 2008
cap:aaai08
We illustrate a general agent model which includes a base level BA and a meta-level MA. The MA performs various forms of meta-reasoning including meta-control, which has the role of making meta-level decisions effective on the BA. As, in our view, meta-reasoning and meta-control are often concerned with time, we introduce the possibility of expressing temporal meta-rules. A very important meta-level activity in evolving agents is learning: we propose a general vision for interacting agents, where agents learn their patterns of behavior not only by observing and generalizing their observations, but also by “imitating” other agents, after being told by them. The process of learning by imitation is based on meta-reasoning about various aspects, from self-monitoring to knowledge evaluation. We propose an operational model for knowledge exchange assuming an agent society which is based on concepts of reputation and trust.
In proceedings
S. Costantini, P. Dell'Acqua, Luís Moniz Pereira
M. T. Cox, A. Raja
Procs. Metareasoning: Thinking about thinking workshop, AAAI08
-
AAAI
-
-
-
-
-
-
http://centria.di.fct.unl.pt/~lmp/publications/online-papers/aaai08.metareasoning_ws.pdf
Export formats
S. Costantini and P. Dell'Acqua and Luís Moniz Pereira, A Multi-layer Framework for Evolving and Learning Agents, in: M. T. Cox and A. Raja (eds), Procs. Metareasoning: Thinking about thinking workshop, AAAI08, AAAI, (http://centria.di.fct.unl.pt/~lmp/publications/online-papers/aaai08.metareasoning_ws.pdf), July 2008.
S. Costantini, <a href="/people/members/view.php?code=c3899b9bc15364381381c58d138af552" class="author">P. Dell'Acqua</a> and <a href="/people/members/view.php?code=6175f826202ff877fba2ad77784cb9cb" class="author">Luís Moniz Pereira</a>, <b>A Multi-layer Framework for Evolving and Learning Agents</b>, in: M. T. Cox and A. Raja (eds), <u>Procs. Metareasoning: Thinking about thinking workshop, AAAI08</u>, AAAI, (<a href="http://centria.di.fct.unl.pt/~lmp/publications/online-papers/aaai08.metareasoning_ws.pdf" target="_blank">url</a>), July 2008.
@inproceedings {cap:aaai08, author = {S. Costantini and P. Dell'Acqua and Lu\'{\i}s Moniz Pereira}, editor = {M. T. Cox and A. Raja}, title = {A Multi-layer Framework for Evolving and Learning Agents}, booktitle = {Procs. Metareasoning: Thinking about thinking workshop, AAAI08}, publisher = {AAAI}, url = {http://centria.di.fct.unl.pt/~lmp/publications/online-papers/aaai08.metareasoning_ws.pdf}, abstract = {We illustrate a general agent model which includes a base level BA and a meta-level MA. The MA performs various forms of meta-reasoning including meta-control, which has the role of making meta-level decisions effective on the BA. As, in our view, meta-reasoning and meta-control are often concerned with time, we introduce the possibility of expressing temporal meta-rules. A very important meta-level activity in evolving agents is learning: we propose a general vision for interacting agents, where agents learn their patterns of behavior not only by observing and generalizing their observations, but also by “imitating” other agents, after being told by them. The process of learning by imitation is based on meta-reasoning about various aspects, from self-monitoring to knowledge evaluation. We propose an operational model for knowledge exchange assuming an agent society which is based on concepts of reputation and trust.}, month = {July}, year = {2008}, }
Publication's urls
/publications/view.php?code=c2a063b257dc3d90067e1d470efb34cf
/publications/view.php?code=cap:aaai08
Go back
Centre for Artificial Intelligence of UNL
Departamento de Informática, FCT/UNL
Quinta da Torre 2829-516 CAPARICA - Portugal
Tel. (+351) 21 294 8536 FAX (+351) 21 294 8541

Fundacao_FCT