When advanced AIs begin to choose their own destiny, one decision they will need to make is whether or not to transfer or copy themselves (software and memory) to new hardware devices. For humans this possibility is not (yet) available and so it is not obvious how such a question should be approached. Furthermore, the traditional singleagent reinforcement-learning framework is not adequate for ...

In E-Commerce today webportals are important and also intelligent agents grow in significance. Our approach is to combine them in designing webportals and interfaces for both users and agents. In this paper we discuss the problems in automatically accessing portals and possible solutions for them through using OOM methods. The solution selected by us, using an XML-based standard and dynamically...

Most of the work since submitting the previous report has concentrated on software implementation. We have developed a platform in which artificial creatures composed of rigid three-dimensional (3D) blocks and controlled by neural networks may interact physically with their environment and with each other. The design of this platform is mostly based on the experiments of Karl Sims [6, 5], with ...

The perspective of modelling agents rather than using them for a specificed purpose entails a difference in approach. In particular an emphasis on veracity as opposed to efficiency. An approach using evolving populations of mental models is described that goes some way to meet these concerns. It is then argued that social intelligence is not merely intelligence plus interaction but should allow...

In this paper we argue that learning or adaptation ability should be included in the basic set of features characterizing an intelligent agent in design. We propose a collection of attributes describing agents, which are grouped into several categories. Next, we present the results of a detailed study of all agents for design, which were discussed during the First International Workshop on Agen...

The topic of getting machines to play classical board games at the same level as top ranking human players, is a research area of artificial intelligence that has received a considerably amount of attention from researchers during the years. But although the area to this point has received quite a lot of attention, and there exist examples of computers that has defeated top ranking human player...

Agents are distinguished for their autonomous and goal oriented characters. To model the complex goals of agents, this paper proposes an agent goal model, namely, composite state goal model, based on Petri Net theory and Object-Oriented methodology. The proposed model not only enables the agent to manage the composite goals, sub goals but also provides the quantitative measurement of partial go...

We are investigating techniques for developing distributed and adaptive collections of agents that coordinate to retrieve, lter and fuse information relevant to the user, task and situation, as well as anticipate a user's information needs. In our system of agents, information gathering is seamlessly integrated with decision support. The task for which particular information is requested of the...

This paper is focused on description of an ongoing project of a multi-agent system application to medical domain. Great interest in multi-agent paradigm is quite natural because a number of software systems have reached such a degree of complexity that it is impossible to control and operate them as monolithic systems. Therefore the effort of decomposition of such systems is a natural procedure...