Shifting the Focus from Control to Communication: the STReams OBjects Environments Model of Communicating Agents

Dugénie

2008

MGS

Self Cite

The GRID and MAS (Multi-Agent Systems) communities believe in the potential of GRID and MAS to enhance each other as these models have developed significant complementarities. Thus, both communities agree on the 'what' to do: promote an integration of GRID and MAS models. However, while the 'why' to do it has been stated and assessed, the 'how' to do it remains a research problem. This paper addresses this problem by means of a service-oriented approach. Services are exchanged (i.e., provided and used) by agents through GRID mechanisms and infrastructure. The paper first consists of a set of states of the art about integration approaches in GRID, MAS and Service-Oriented Computing (SOC). It secondly proposes a model for GRID-MAS integrated systems. Concepts, relations between them and rules are semantically described by a set-theory formalization and a common graphical description language, called Agent-Grid Integration Language (AGIL). This language may be used to describe future GRID-MAS integrated systems. AGIL's concepts are directly influenced by OGSA (Open Grid Service Architecture) and the STROBE agent communication and representation model.

Section: Status Of Current Integration Activitiesmentioning

confidence: 99%

Section: The Strobe Modelmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Agent-Grid Integration Language

Dugénie

2008

MGS

Self Cite

“…In the STROBE (STReams, OBjects, Environments) [2] model, that inherits most of its features from classical lambda calculus [8], denotational semantics [9] and the Scheme language we have identified a few basic properties for Agents:…”

Section: The Strobe Model and Its Evolutionmentioning

confidence: 99%

Dynamic Learning Agents and Enhanced Presence on the Grid

Eisenstadt

Electronic Workshops in Computing

2003

Self Cite

Human Learning on the Grid will be based on the synergies between advanced software and Human agents. These synergies will be possible to the extent that conversational protocols among Agents, human and/or artificial ones, can be adapted to the ambitious goal of dynamically generating services for human learning. In the paper we highlight how conversations may procure learning both in human and in artificial Agents. The STROBE model for communicating Agents and its current evolutions shows how an artificial Agent may "learn" dynamically (at run time) at the Data, Control and Interpreter level, in particular exemplifying the "learning by being told" modality. The enhanced telepresence research, exemplified by Buddyspace, in parallel, puts human Agents in a rich communicative context where learning effects may occur also as a "serendipitous" side effect of communication. The integration of the two streams of research will be the result of a workpackage within the E-LeGI EU Integrated Project, currently under negotiation.

“…Conversations and their states are represented in the STROBE model by cognitive environments. We can explore further the concept of cognitive environments, 8 which is a relatively new, but very important, concept related to the STROBE agent and communication model [8,9,29,30]. In the STROBE model agents are able to interpret communication messages in a given conversation context that includes an interpreter, dedicated to the current conversation.…”

Section: Agil's Conceptsmentioning

confidence: 99%

Service-Based Integration of Grid and Multi-Agent Systems Models

Dugénie

Service-Oriented Computing: Agents, Semantics, and Engineering

Self Cite

Abstract. This position paper addresses the question of integrating GRID and MAS (Multi-Agent Systems) models by means of a service oriented approach. Service Oriented Computing (SOC) tries to address many challenges in the world of computing with services. The concept of service is clearly at the intersection of GRID and MAS and their integration allows to address one of these key challenges: the implementation of dynamically generated services based on conversations. In our approach, services are exchanged (i.e., provided and used) by agents through GRID mechanisms and infrastructure. Integration goes beyond the simple interoperation of applications and standards, it has to be intrinsic to the underpinning model. We introduce here an (quite unique) integration model for GRID and MAS. This model is formalized and represented by a graphical description language called Agent-Grid Integration Language (AGIL). This integration is based on two main ideas: (i) the representation of agent capabilities as Grid services in service containers; (ii) the assimilation of the service instantiation mechanism (from GRID) with the creation of a new conversation context (from MAS). The integrated model may be seen as a formalization of agent interaction for service exchange.