In this paper we sketch a model in which agents are autonomous not only because they can choose among alternative courses of action (executive autonomy), but also because they can select and pursue new goals on the basis of endogenously generated interests (goal autonomy). We use economic models to argue that goal autonomy can be defined by introducing a precise notion of an agent’s identity. 1...

Autonomous group agents coordinate cooperative activities in spatially distributed groups of people who communicate via electronic mail. The highly asynchronous nature of remote communication poses a problem for the design of such programmed agents. This paper describes a tool supporting the consistent design of the communication behaviour of autonomous group agents. The tool will support the d...

Agents 2000 conference last month in Barcelona, we went souvenir shopping. On the outskirts of the city, an old man in a dilapidated store had some interesting wares, but he spoke only Catalan and we spoke only English and Polish. Nevertheless, even without a common language, we managed to reach an agreement. We left not only with the souvenirs but also knowing their names in Catalan. How did t...

TALKING ABOUT MENTAL STATES McCarthy gives reasons why we shall need to describe intelligent robots in mentalistic terms, and why such a robot will need some degree of self consciousness, and he has made suggestions regarding the notation that we and the robot might use to describe its states. This talk extends that work by focusing on the underlying “high level” architectures required to justi...

The Agent Development Environment is an integrated platform for building distributed multi-agent applications. ADE enables a graphical definition of Agents and Agents’ Activities. ADE provides a simulation environment in which Agents can be tested before being deployed. ADE is built on G2, an object-oriented graphical environment that offers a robust platform for the development of real-time sy...

We present some results of our research in the field of Machine Learning applied to robotics problems. In particular we have investigated on: (i) the application of Learning Classifier Systems to the synthesis of robot controllers; (ii) learning of fuzzy controllers; (iii) learning of purposeful representations of the environment; (iv) and the application of versions of Q-learning to robot trai...

Mat chapters in this baak foars on sone aspect ol spuifcally |dnnan costtilion. Raruly Ben, by conbast, here takes as his imnediLle taryet the behapiors of sinple' a*ifcidl, ircectlike creatufts.'Yet the issues nised and the ltsights gained go ditectly to the hea* of what it is to r derctanl krma cogtlitiott itself The latto parL of this chaptet contai s a discttssion af detailai nadelins Hele ...

Utility theory and the principle of maximising the expected utility have, within the multi-agent community, had a great influence on multi-agent based decision. Even though this principle is often useful when evaluating a decision situation it is virtually impossible, except in very artificial situations, to use the more basic decision rules with its unrealistically strong requirements for the ...

Often, decision making involves autonomous agents that are structured in a complex hierarchy, representing e.g. authority. Typically the agents share the same body of knowledge, but each may have its own, possibly conflicting, preferences on the available information. We model the common knowledge base for such preference agents as a logic program under the extended answer set semantics, thus a...