Communicative Actions for Arti cial Agents
نویسندگان
چکیده
This paper considers the semantics of the agent communication language KQML. By using this language for communication, agents will be able to request and provide services. Indeed, numerous projects have shown how the language can pro tably support interoperation among distributed agents. However, before becoming a widely-accepted standard, it would be worthwhile to examine the language in detail, especially the semantical issues it raises. This paper identi es numerous di culties with the language, and an attempt is made to point to their resolution. The paper illustrates the kind of semantics we believe to be necessary to characterize agent communication languages, identi es an important adequacy condition (compositionality) and shows how to compose a question from a request and an inform. Finally, the paper discusses possible impacts to be felt on various KQML decisions from the semantical issues raised here.
منابع مشابه
Can a Rational Agent Afford to be Affectless? A Formal Approach
In this article, we expose some of the issues raised by the critics of the neoclassical approach to rational agent modeling and we propose a formal approach for the design of arti cial rational agents that includes some of the functions of emotions found in the human system. We suggest that emotions and rationality are closely linked in the human mind (and in the body, for that matter) and, the...
متن کاملProlegomena to any future artificial moral agent
As arti® cial intelligence moves ever closer to the goal of producing fully autonomous agents, the question of how to design and implement an arti ® cial moral agent (AMA) becomes increasingly pressing. Robots possessing autonomous capacities to do things that are useful to humans will also have the capacity to do things that are harmful to humans and other sentient beings. Theoretical challeng...
متن کاملLearning to Speculate: Experiments with Arti cial and Real Agents
This paper employs an arti cial agent{based computational approach to understanding and designing laboratory environments in which to test Kiyotaki and Wright's search model of money. The behavioral rules of the arti cial agents are modeled on the basis of prior evidence from human subject experiments. Simulations of the arti cial agent{based model are conducted in two new versions of the Kiyot...
متن کاملArti cial Agents and Logic Programming Gerd
Arti cial agents represent a new paradigm in software engineering and Arti cial Intelligence. As complex software-controlled systems they are capable of exible autonomous behavior in dynamic and unpredictable environments. Over the past few years, researchers in computer science have begun to recognise that the technology of arti cial agents provides the key to solving many problems in distribu...
متن کاملOn computational social laws for dynamic non-homogeneous social structures
Approaches to the coordination of arti cial agents may be inspired by observations on human and other natural societies. On the other hand, the introduction and the analysis of general computationalmodels and mechanisms of coordination may shed light on the general theory of coordination. This paper extends a fundamental approach to the coordination of arti cial agent societies, the arti cial s...
متن کاملCoordination through Plan Repair
In most application domains for distributed arti cial intelligence, several autonomous agents (e.g., companies or personal assistants) each have their own goals. They need to plan for these goals, coordinate their actions, deal with uncertainty, and interleave all this with plan execution [2, 4]. To complicate matters even more, many agents are self-interested and require some privacy concernin...
متن کامل