=Paper=
{{Paper
|id=Vol-57/paper-6
|storemode=property
|title=ABROSE : Multi Agent Systems for Adaptive Brokerage
|pdfUrl=https://ceur-ws.org/Vol-57/id-7.pdf
|volume=Vol-57
|authors=Marie-Pierre Gleizes and Pierre Glize
|dblpUrl=https://dblp.org/rec/conf/aois/Glize02
}}
==ABROSE : Multi Agent Systems for Adaptive Brokerage==
https://ceur-ws.org/Vol-57/id-7.pdf
ABROSE: Multi Agent Systems for Adaptive
Brokerage
Marie-Pierre Gleizes, Pierre Glize
Institut de Recherche en Informatique de Toulouse
Université Paul Sabatier
31062 Toulouse, Cedex 4, France
{gleizes, glize}@irit.fr
http://www.irit/SMAC
1. Context of the Project
A market place is composed of an important amount of content providers and custom-
ers who have very dynamic offers and requests. ABROSE1 (Agent based BROkerage
SErvices in electronic commerce) is an agent-based electronic commerce tool. The
principal idea is to use an agent-based collective memory between content providers
and customers which contains the users’ individual experiments results. ABROSE
manages this collective memory to improve the exchanges quality. The principal func-
tions offered by ABROSE are:
- for the customers, simplified interactions, a personalized assistant, spontaneous
notification of new offers, a navigation and requests formalisation tool , a list of rele-
vant content providers which answer to a request given by the customer.
- for the content providers, a target diffusion of the offers towards relevant custom-
ers, a collection of information about the customer’s interests and about market offers.
2. The Architecture of ABROSE
The prototype ABROSE V2.0 is implemented in Java with JWS1.1.3, the communica-
tion between the multi-agent system and the other parts of the system is supported by
OrbixWeb3.1™. The brokerage software, which includes the multi-agent systems,
runs on Solaris 2.6. The customer is a Personal Computer with the standard browser
Netscape™. ABROSE is composed of two main parts: the broker domain and the user
domain assuming the access to information and the displaying abilities for a user. The
part of the system which realises the brokerage in ABROSE is constituted of several
adaptive multi-agent systems: the multi-agent system of transaction agents and multi-
1 European ACTS project with nine partners: Deutsche Telekom Berkom, InfoMures SA Roumanie,
France Telecom CNET, Universidad Polytechnica de Madrid, Onyx Ltd Angleterre., Dégriftour SA
Paris , National Technical University of Athens, Technical University of Berlin, IRIT Université Paul
Sabatier of Toulouse.
agent systems of belief agents. At the most general level, there is the Mediation Agent
(MA) representing the site where ABROSE is located. A MA knows all the Transac-
tion Agents (TA) present on the site. The MA has beliefs on the TAs which evolve in
an independent way from the evolution of the beliefs of TAs. The beliefs of the MA
are not a simple aggregation of the belief of all TAs, but rather a synthetic view.
At the middle
level, the system is
composed of an CA UAM CA
adaptive multi- Spy Spy
agent system of the
TAs present on the AMA TA 1 TA 2 . . . TA n AMA
site. A TA repre-
sents a customer or NA NA
Multi-agent
MA
a content provider system
FE
and belongs to Customer
Terminal
Content Provider
Terminal
him. It knows BM
User Domain Broker Domain User Domain
other TAs that are Operator Terminal
on its site, but has OT
no global view.
Figure 1: ABROSE global architecture
At the lowest level, the beliefs possessed by the MA about itself and those pos-
sessed by a TA about itself and about other TAs are implemented in an adaptive multi-
agent system called Belief Network (BN). There is a BN per TA and the MA also has
a BN.
An adaptive multi-agent system is a system composed of agents which are in inter-
action with the environment, and which modifies their interactions in a self-organising
process. In a general way, the system-environment exchanges imply reciprocal influ-
ences which bring about a mutual adjustment due to their structural coupling. The
unexpected happenings were inherent to the life of these systems. It is why the self-
organisation which is an autonomously change becomes a way to arrive to overcome
the perturbations of the environment. For a system S learning consists in autono-
mously modifying its actual function, noted fS, in order to adapt itself to its environ-
ment. The environment is considered as a constraint given to the system. Each part pi
of the system S realises a partial function fpi. The environment of a part pi is com-
posed of the other parts of the system and the environment of S. The global function fs
is the result of the composition of these fpi. The composition is determined by the
relations - i.e. the organisation - that connect the parts. So, without changing the parts,
transforming the internal organisation of the system leads to a change of the composi-
tion between the partial functions and consequently leads to a change of the global
function fs. The theory of AMAS (Adaptive Multi-Agent Systems) that we have stud-
ied and used, asserts that a permanent cooperation state between the parts of the sys-
tem guarantees the functional adequacy of the whole system. A system which is func-
tionally adequate realises the right activity. And we have shown that for any function-
ally adequate system in a given environment there is at least a system having its parts
(or agents) in cooperative interactions, which realises an equivalent function. The
concrete implication of this theory allows a system to adapt itself when faced with a
dynamic environment and gives us a guide to design multi-agent systems. For the
design phase, we focus on cooperative agents and on finding local criteria from the
point of view of an agent in order to determine non cooperative interactions and to
remove them. The self-organisation based on cooperation implies that the system and
its environment try to mutually adjust themselves to be in cooperative interactions, and
implies at a different level that all the agents of the system try also to be in cooperative
interactions.
3. Transaction Agents
TAs are built when a new service is created or when a customer registers to ABROSE.
TAs co-operate with each other to answer to a request or to propagate an offer. Each
TA consists in beliefs, skills, an interaction language and social attitudes. The skills of
a TA are the skills of the user it represents. When a TA receives a message, it inter-
prets it and acts. The beliefs describe the knowledge a TA possesses about the others
and about its own skills. The social attitude is cooperation; it is guiding its behaviour.
TAs interact with others by messages exchanges. They use protocols and speech acts,
as a subset according to FIPA definition. TAs represent the parts of an adaptive multi-
agent system. They try to maintain all the time, cooperative interactions between
themselves. In order to do this, each TA is endowed with a cooperative social attitude
that gives it three properties: Sincerity: an agent says the truth about something it
knows. Willingness: an agent tries to satisfy a received request if it is coherent with its
own skills. Reciprocity: an agent knows that the others belonging to the same society
have the same social attitude as itself. An agent cannot act if it has no belief about
others. In consequence, a cooperative agent sends spontaneously information to an-
other agent, if it believes it is useful to the receiver. If an agent is unable to satisfy a
given request, it automatically recruits other agents that have relevant skills on the
subject. A TA which does not know to answer to a received request (or offer) can
request assistance of known TAs if it thinks they are relevant, or of the MA which has
a global point of view about the market place. When a TA represents a customer (re-
spectively a content provider), the trigger conditions for learning and the moment
when the belief of this TA evolves, are the following one:
1- When a new request (respectively offer) is given to the TA, it learns that the cus-
tomer is interested by the request (respectively that the content provider could answer
to the offer),
2- when he evaluates the received offer or when he evaluates the realised transac-
tion, it learns on itself and on the content provider who has given the offer or who has
answered to the request,
3- if it has requested assistance of the MA, the TA learns on the content providers
(respectively on potential customers) communicated by the MA,
4- if it receives an answer from a content provider (respectively from a customer)
by an other TA, it learns on the content provider (respectively from a customer).
During the lifetime of the system, the interactions between TAs evolve: the self-
organisation process is responsible of the evolution of the mutual belief. Conse-
quently, the organisation between the TAs evolves too.
4. Conclusion
The European project is ended; the final software version was tested in real connection
to the electronic commerce server of Tradezone. Using it has shown that the multi-
agent technology is useful to solve problems in a dynamic environment like a market
place and that the brokerage service quality was improved because of the use of a
collaborative, adaptive and altruistic society. Nevertheless, ABROSE has some short-
comings. It was never used with a huge collection of products; we evaluated it only in
using approximately five hundred products descriptions. The response time was really
correct for the end-user with the configuration used but we have no test with thou-
sands of users yet. Because of privacy reasons on users’ personal information, a user
needs to subscribe to have a password to access private information.The essential
properties of the ABROSE system could be summed up in five points. Firstly, the
system is modular and reusable because the code of the communication between
agents, the code of the BN could be reused in others applications. Secondly, it is ge-
neric: ABROSE could be used for selling or promoting any products or service.
Thirdly, in ABROSE several languages could be used. The content providers could
describe their products or services in any language (perhaps in several); it is implicit
that the requests may be done in the same language. Fourthly, ABROSE is an open
system because the creation or the removal of transaction agents is dynamically done
without any human intervention. Fifthly, ABROSE adapts itself by taking into account
in real time and automatically the evolution of its environment (the users’ preferences
and the content providers’ services).
References of the ABROSE project
1. Athanassiou Eleutherios, Chirichescu Délia, Gleizes Marie-Pierre, Glize Pierre, , Lakoumen-
tas Nikos, Schlenker Hans, Leger Alain, Moreno Jose-Ignacio - Abrose : A Co-operative
Multi-Agent Based Framework for Marketplace - IATA, Stockholm, Sweden August 1999
2. Einsiedler Hans Joachim., Gleizes Marie-Pierre, Léger Alain - Abrose : A Co-operative
Multi-Agent Based Framework for Electronic Marketplace - Infowin-Infobridge: Book about
"Agent Technology", ACTS related publication November 1999
3. Gleizes Marie-Pierre, Léger Alain, Athanassiou Eleutherios, Glize Pierre - Abrose : Self-
Organization and Learning in MultiAgent based Brokerage Services - 6th International Con-
ference on Intelligence and Services in Networks, IS&N'99, Barcelona, Spain proceedings pp
41-54., Lecture Notes in Computer Science 1597, Springer 26-28 April 1999
4. Glize Pierre, Gleizes Marie-Pierre, Léger Alain - Brokerage Communication in a Co-
operative Multi-Agent Based Mediation Service: One Example in Abrose - FIPA, cfp6-016,
Nice (F) 12-16 April 1999