S. Calderoni. World Multiconference on Systemics, Cybernetics and
Informatics SCI-99, 7, (1999)
Abstract
This paper reports on-going works dealing with
collective learning in autonomous agents context. We
propose a methodology to design robust and flexible
adaptive behavior with both genetic and reinforcement
learning techniques.The originality of this
contribution relies on the ability of the agents to
manage themselves their learning task. Indeed, rather
than coming from the environment, as it is implemented
in many programs, we consider that the reinforcement
must be intrinsically deduced by the agent itself, from
satisfaction and disapointment indicators. We show that
in such a way, the agents are capable of robustness
facing with unexpected situations. A collective
regulation problem is presented to help in clarify the
different issues tackled in this paper. A software
toolkit has been developped as a support for these
works.
%0 Conference Paper
%1 oai:CiteSeerPSU:247844
%A Calderoni, Stephane
%B World Multiconference on Systemics, Cybernetics and
Informatics SCI-99
%D 1999
%K Control Learning Multiagent Reinforcement Systems, algorithms, genetic programming,
%T Generic Control Ssystem in MultiAgent Domain
%U http://citeseer.ist.psu.edu/247844.html
%V 7
%X This paper reports on-going works dealing with
collective learning in autonomous agents context. We
propose a methodology to design robust and flexible
adaptive behavior with both genetic and reinforcement
learning techniques.The originality of this
contribution relies on the ability of the agents to
manage themselves their learning task. Indeed, rather
than coming from the environment, as it is implemented
in many programs, we consider that the reinforcement
must be intrinsically deduced by the agent itself, from
satisfaction and disapointment indicators. We show that
in such a way, the agents are capable of robustness
facing with unexpected situations. A collective
regulation problem is presented to help in clarify the
different issues tackled in this paper. A software
toolkit has been developped as a support for these
works.
%Z The Pennsylvania State University CiteSeer Archives
@inproceedings{oai:CiteSeerPSU:247844,
abstract = {This paper reports on-going works dealing with
collective learning in autonomous agents context. We
propose a methodology to design robust and flexible
adaptive behavior with both genetic and reinforcement
learning techniques.The originality of this
contribution relies on the ability of the agents to
manage themselves their learning task. Indeed, rather
than coming from the environment, as it is implemented
in many programs, we consider that the reinforcement
must be intrinsically deduced by the agent itself, from
satisfaction and disapointment indicators. We show that
in such a way, the agents are capable of robustness
facing with unexpected situations. A collective
regulation problem is presented to help in clarify the
different issues tackled in this paper. A software
toolkit has been developped as a support for these
works.},
added-at = {2008-06-19T17:35:00.000+0200},
annote = {The Pennsylvania State University CiteSeer Archives},
author = {Calderoni, Stephane},
biburl = {https://www.bibsonomy.org/bibtex/20565e7b0d05ba746bbf49d3e082bed59/brazovayeye},
booktitle = {World Multiconference on Systemics, Cybernetics and
Informatics SCI-99},
citeseer-isreferencedby = {oai:CiteSeerPSU:26950},
interhash = {575086e6645f74d40e8bf3c3051a95fb},
intrahash = {0565e7b0d05ba746bbf49d3e082bed59},
keywords = {Control Learning Multiagent Reinforcement Systems, algorithms, genetic programming,},
language = {en},
oai = {oai:CiteSeerPSU:247844},
rights = {unrestricted},
timestamp = {2008-06-19T17:37:15.000+0200},
title = {Generic Control Ssystem in MultiAgent Domain},
url = {http://citeseer.ist.psu.edu/247844.html},
volume = 7,
year = 1999
}