Franklin, S., & Graesser, A. (1996). Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. In Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages. Amsterdam: Springer-Verlag.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....agents based on these standards. 2.1 Software Embodiment In many ways, all research on coevolving EC systems is apropos to agent based systems. However, EC systems that use actual software agents have been rare. This paper will not attempt to enter the debate on what constitutes a software agent [Franklin and Graesser, 1997]. Instead, we only suggest that there are general purpose, agent based system standards emerging, and that few EC systems have been placed within standards based agent frameworks. To implement an EC system, a programmer typically writes computer code that creates a population of software ....

Franklin, S. and Graesser, A. (1997). Is it an agent, or just a program? : A taxonomy for autonomous agents. In Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages, pages 21-- 35. Springer-Verlag.

....as anything that perceives its environment through sensors and acts upon the environment through effectors [Russel and Norvig 1994] More specific definitions are provided with the concatenation of some term near the word agent. Software agents [Genesereath and Ketchpel 1994] autonomous agents [Franklin and Graesser 1996] or mobile agents [Hofman et al. 1998] and collaborative programmable intelligent agents [Nardi et al. 1998] are possible variations, emphasizing communication languages between agents, or otherwise their ability to live and perform actions autonomously locally or remotely and finally, their ....

FRANKLIN, S. AND GRAESSER, A. 1996. Is it an Agent, or Just a Program ? A Taxonomy for Autonomous Agents. In Proceedings of the Third International Workshop on Agent Theories, Architectures and Languages.

....no agreed upon, formal definition for the term agent in a computational context, a functional definition is provided here through a review of the various characteristics and abilities that have been used to describe agents in research literature. Some of these characteristics and abilities include [33, 35]: the autonomous representation of another entity, the ability to communicate, interact, and collaborate with other entities, the ability to perceive, move through, react to, and alter a complex, dynamic environment, the ability to reason, learn, and adapt, and . the ability to take ....

S. Franklin & A. Graesser (1997) Is it an Agent, or Just a Program?: A Taxonomy for Autonomous Agents. Proc. of the Third Int. Workshop on Agent Theories, Architectures, and Languages, pp. 21-35.

....are cloned and moved to the user environment to build the perspective in the VRML world. Enforcing a perspective onto another user is accomplished by cloning and moving the display agents from one user to another. Now why can we call these entities agents There are a lot of definitions of agents (Franklin Graesser 1996), and the question can be raised why a display agent is an agent. In other words, how does it differ from a standard program or software component For one, the agents are autonomous, which means they execute on their own. Second, they react on certain input and subsequently act on their ....

....they have knowledge of. This domain is the visualization of information. Fifth, they act on behalf of a user. Users can give their preferences to a display agent, and the agent will take care of it. All in all, the display agent fits quite a number of definitions of autonomous agents given by Franklin Graesser (1996). Controllers Every DIVA component can have a separate mobile controller. It can be moved from one environment to another, so it can be shared by several participants. The ability to use a controller depends on the role of the user. Participants can request a controller or the chair could appoint ....

Franklin, S. & Graesser, A. (1996), Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents, in `Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages'.

....first look at agent research in general before looking at issues related to existing pedagogical agents which will inform this discussion. Agents So, the first question has to be what is an agent I do not intend to get embroiled in this question as it is very much a contentious issue (see Franklin Graesser, 1996). Reaching an agreeable definition of a concept is nearly always a arduous process. However, I will give a brief overview of the main issues before making clear what I believe is important in this area in terms of making a contribution to research in on line study guides. As stated, there is much ....

....is important and that one program may be viewed as an agent by one person and not by another. I do not intend to go into any further depth regarding the definition of an agent as I do not believe it will aid this discussion. For further discussion on what an agent is and a taxonomy of agents see Franklin and Graesser, 1996). What I now intend to do is to look at some issues arising from agent research which will be pertinent to this discussion. Although brief, the above discussion has highlighted two aspects of an agent its functionality and its manner of portrayal. Erickson (1997) refers to this as an agent s ....

Franklin, S., & Graesser, A. (1996). Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. Paper presented at the Third International Workshop on Agent Theories, Architectures, and Languages, Springer-Verlag.

....Even a cursory examination of the literature from the study of agents would reveal that it is traditional, if not in fact ritual, to refer to the lack of consensus agreement amongst researchers on what the generic term agent means. Some [Wooldridge, 1995] dismiss this as hardly mattering; others [Franklin, 1996] and [Bradshaw, 1997] extensively review, seeking to find common ground amongst the agent community. There is, however, little consensus amongst agent researchers about the nature of agents and agency. It may be useful to remember that there is no shared common definition of intelligence amongst ....

Franklin, S. G., A. (1996). Is it an Agent, or just a Program: A Taxonomy for Autonomous Agents. Proceedings of the Third International Workshop on Agent Theories, Architectures and Languages., Springer-Verlag.

....formal version of mental states, which dictate the agent s actions and which are affected by messages they receive. An agent (within the context of this work) is a system that as a part of a virtual environment receives information from its environment and influences it to reach specific goals [Franklin96]. A crucial criteri on for an agent is its autonomy. That means, that it has the ability to act, is independent and has the control over its internal state. An intelligent agent is a computer system that is able to act flexibly and autonomously in a certain environment. That implies that it acts ....

Franklin, S., Graesser, A. (1996). Is it an Agent, or just a Program? in: Proceedings of the Third International Workshop on Agent Theories, Architectures and Languages, Springer-Verlag

.... is capable of flexible autonomous action in order to meet its design objectives [1] An autonomous agent is a system situated within, and a part of, an environment that senses that environment and acts on it over time in pursuit of its own agenda and so as to effect what it senses in the future [2]. The term agent is used to denote a computer systems that enjoys the following properties [1, 3] Autonomy; agents operate without the direct intervention of humans (or other agents) and have control over their own actions and internal state. In a stronger sense, they are systems capable of ....

Franklin, S., Graesser A. (1996). Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages. Springer-Verlag, 1996.

.... In fact, the term has been used to describe everything from a word processor Help system to mobile code that can roam networks to our bidding (Wayner, 1995) There exist several definitions of agents, given by different researchers, each involving the characteristics most valuable to them (Franklin and Graesser, 1996). We have chosen Wooldridge and Jennings (1995) because although it is a very general definition it includes key features that will provide an initial classification of agents: An agent is a self contained problem solving entity implemented in hardware, software or a mixture of the two that ....

....Proactiveness : agents should not only act in response to their environment, they should be able to take advantage of fortuitous opportunities to achieve their designated goals. An agent should be able to modify its behaviour in response to stimuli. Agents can be classified in several ways (read Franklin and Graesser (1996) and Wooldridge and Jennings (1995) for some classifications) Because this paper is concerned with the application of agents to spatial issues, we will discuss only the types of agents that will be useful in this area of expertise: Mobile Agents, Reactive Agents, Cognitive Agents and Interface ....

[Article contains additional citation context not shown here]

Franklin, S., Graesser, A. (1996), Is it an Agent, or just a Program ?: A Taxonomy for Autonomous Agents, <http://www.msci.memphis.edu/~franklin/AgentProg.html>, Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages, Springer-Verlag, 1996.

....we mean by such terms as agent and agent based system . Unfortunately, we immediately run into difficulties, as some key concepts in agentbased computing lack universally accepted definitions. In particular, there is no real agreement even on the core question of exactly what an agent is (see Franklin and Graesser (1996) for a discussion) However, we believe that most researchers 4 Jennings and Wooldridge would find themselves in broad agreement with the following definitions (Wooldridge and Jennings, 1995) First, an agent is a computer system situated in some environment, and that is capable of autonomous ....

Franklin, S., Graesser, A. (1996) Is it an agent, or just a program? Proceedings Third International Workshop on Agent Theories, Architectures and Languages, Budapest, Hungary, 193-206.

....aims to address these problems. 1 If the interactions are stochastic, we assume that the type of interaction and its possible outcomes are known in advance. MODELLING MULTI AGENT SYSTEMS The term agent is used in many different senses in the agent based systems literature (see, for example, (Franklin Graesser 1997)) For the purposes of this paper, we shall define an agent as a self contained, concurrently executing thread of control that encapsulates some state and communicates with its environment and possibly other agents via some sort of message passing (Wooldridge Jennings 1995) There are many ....

Franklin, S. & Graesser, A. (1997), Is it an agent, or just a program?: A taxonomy for autonomous agents, in `Intelligent Agents III: Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages', Vol. 1193 of Lecture Notes in Artificial Intelligence, Springer-Verlag, pp. 21--35.

....of behavior oriented AI (cf. section 2.3) much of its basic terminology is still ill defined. The term agent , for example, is unfortunately used for all sorts of systems, ranging from the most complex (humans, animals) to the very simple (programs, subroutines, etc. cf. Franklin Graesser, 1996; Woolridge Jennings, 1995) In line with Beer s above definition, in this paper an agent is to be understood as a system that can be viewed as situated in an environment, and interacting with it by means of perception and action. The use of the term behavior is twofold: On the one hand it can ....

Franklin, S. & Graesser, A. (1996). Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. Proceedings of Third International Workshop on Agent Theories, Architectures, and Languages. Berlin/Heidelberg, Germany: Springer Verlag.

....or contract is in the mind of some agent rather than being something possessed by the task itself. Nevertheless, there has been a lot of confusion about this term, especially outside the Distributed Artificial Intelligence community. An interesting survey on possible agent definitions is given in (Franklin and Graesser 1996). Throughout this paper, I will use the term agent to denote an artificial representative, which autonomously acts in behalf of a human or organizational actor in the application domain. For presentation, I will follow a small example out of an industrial size case study. This case study is ....

Franklin, S. and Graesser, S. 1996. Is it an Agent, or just a Program: A Taxonomy for Autonomous Agents. In Proceedings of the 3rd International Workshop on Agent Theories, Architecture, and Language (ATAL):193--206.

....as well as self regulating. They determine the paths they follow as well as steer along them. 2 An agent should here be understood as a system that interacts with an environment through perception and action. For an overview and detailed discussion of a large variety of notions of the term see Franklin and Graesser (1996) 3 It should be noted that the world Brooks refers to in the above quote is the physical world out there (in this paper referred to as environment ) whereas the term world in Bourgine Varela s sense (cf. earlier quote) refers to an agent s interpretation of the environment , ....

Franklin, S. A. and Graesser, A. (1996). Is it an agent, or just a program?: A taxonomy for autonomous agents. In Proceedings of Third International Workshop on Agent Theories, Architectures, and Languages, Heidelberg, Germany.

....and so forth. This author is content to use Franklin s definition of an agent: An autonomous agent is a system situated within and a part of an environment that senses that environment and acts on it, over time, in pursuit of its own agenda and so as to effect what it senses in the future. (Franklin Graesser, 1996) On this definition a simple thermostat, a negative feedback control system, is an agent. However, most AI agents are much more complex than a thermostat. There are at least two uses of the word architecture ; one referring to an abstraction or design that is common to many instances of the ....

Franklin, S. & Graesser, A. (1996). Is it an agent, or just a program?: A taxonomy for autonomous agents. In Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages. Springer-Verlag.

....examples. In the conclusion, we identify some open problems and discuss some issues in the design of toolkits. Agent as a cluster concept Despite a number of attempts, there is no widely agreed definition of what constitutes an agent (see, for example, Wooldridge Jennings 1995; Nwana 1996; Franklin Graesser 1997)) It has been argued that this is not necessarily a problem: if many people are successfully developing and implementing interesting and useful applications, then it does not matter whether they agree on terminological details (Wooldridge Jennings 1995) However, if we are to compare agent ....

....has led some to claim that this definition does not distinguish an interesting new class of system. For example, Franklin has argued that Wooldridge and Jennings weak notion of agency could apply to a payroll program with a graphical interface and a decidedly primitive communication language (Franklin Graesser 1997). Franklin goes on to propose an alternative definition based on the notion of an autonomous agent : agent B if the features of A are a superset of the features of B. An autonomous agent is a system situated within and a part of an environment that senses that environment and acts on it, over ....

[Article contains additional citation context not shown here]

Franklin, S., and Graesser, A. 1997. Is it an agent, or just a program?: A taxonomy for autonomous agents.

....systems there is a desired output for every input vector. For our architecture, however, there is only desired input. An agent based on this architecture must be situated within an environment and, by its actions, be able to change its environment in a way that it can sense the change (Franklin and Graesser 1997). What this means for learning is that such an agent should be choosing its actions in such a way as to manipulate its environment so that the agent receives the greatest pleasure or avoids displeasure. This is different from the classic reinforcement scheme (Watkins 1989) where a simple positive ....

....it evokes. This association then acts much like an inhibitory or excitatory behavior increasing or decreasing the likelihood that a particular action is chosen. For our current implementation, the emotion codelets will effect the drives of the system which will, in turn, effect the behavior net (Franklin 1997). However, future work will attempt to determine if complex behaviors can be emergent without the use of explicit drive and goal generation modules. Conscious Mattie A version of the architecture described above is being implemented in a system called Conscious Mattie (CMattie) CMattie ....

[Article contains additional citation context not shown here]

Franklin, Stan and Graesser, Art 1997. Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. Intelligent Agents III, Berlin: Springer Verlag, 21-35.

....complex and lose generality when faced with constrained problems or multi modal problems. They are also weak methods, but they can produce satisficing optimization. Holland s suggestion of combining GA with Economic Agent processing has several interesting potential features, when combined with Franklin (1995, 1997). Agents are autonomous, they have goals and drives, they can sense their environment and change it. Economic agents additionally obey hard and soft constraints and allocate resources efficiently. A group of economic agents can obtain a globally feasible solution to a multi modal problem with a ....

Franklin, Stan. Graesser, Art. 1997. Is it an Agent, or just a Program? : A Taxonomy for Autonomous Agents. In proceedings of Third International Workshop on Agent Theories, Architectures and Languages. Intelligent Agents III. Berlin. Springer-Verlag. 21-35.

No context found.

Franklin, S., & Graesser, A. (1996). Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. In Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages. Amsterdam: Springer-Verlag.

No context found.

Franklin S. and Graesser A. (1996). Is it an Agent, or just a Program? A Taxonomy for Autonomous Agents, In: 3rd Intern. Workshop on Agent Theories, Architectures, and Languages.

No context found.

Franklin, S. and Graesser, A. (1997). Is it an agent, or just a program? A taxonomy for autonomous agents. In Intelligent Agents III, Agent Theories, Architectures, and Languages, volume 1193 of Lecture Notes in Computer Science, pages 21{ 35, Budapest, Hungary. Springer-Verlag.

No context found.

Franklin, S. and Graesser, A. (1996). Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents. Third International Workshop on Agent Theories, Architectures, and Languages, Springer-Verlag.

No context found.

Franklin and Graesser (1997). Is it an agent, or just a program?: taxonomy for autonomous agents. In Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages. Springer-Verlag. pp. 21- 35.

No context found.

S. Franklin and A. Graesser. 1996. Is It an Agent, or Just a Program?: A Taxonomy for Autonomous Agents. In J. P. Muller, M. J. Woolridge, and N. R. Jennings, editors, Intelligent Agents III. Agent Theories, Architectures, and Languages., pages 21-35, Berlin. Springer.

No context found.

Franklin, S and Graesser, A.(1996) Is it an Agent, or just a Program?: A Taxonomy for Autonomous Agents, Proceedings of the 3rd Int. Workshop on Agent Theories, Architectures, and Languages, Berlin, Springer-Verlag

First 50 documents

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC