The building of cooperative multi-agent systems is an issue of growing importance in the field of Distributed Artificial Intelligence. We introduce a type of agency, called dynamic agency, that overcomes the critical problem of having agents that have both several specific operation functions, and one uniform cooperation ability. A dynamic agency is also suited to give flexibility with respect ...

We present a unique and elegant graphics hardware realization of multi agent simulation. Specifically, we adapted Velocity Obstacles that suits well parallel computation on single instruction, multiple thread, SIMT, type architecture. We explore hash based nearest neighbors search to considerably optimize the algorithm when mapped on to the GPU. Moreover, to alleviate inefficiencies of agent le...

AI applications are increasingly moving to artiicial agents, i.e. systems that independently handle parts of the problem based on small independent knowledge bases Gros 1 10, 27]. This study focuses on a speciic class of agents called \reactive agents", which use minimal communication between agents, and rely mostly on changes in the environment as their cue for action. Some early successes of ...

We propose in this paper a model for agentbased devices enhanced with reasoning and interactive features. More precisely, we present an interaction protocol that enables agents to answer received messages, according not only to their functionalities, but also to their role in the interaction they are involved into. This interaction protocol aims at making it possible for agents associated to ph...

Healthcare professionals, working in hospitals experience a high level of mobility due to their need for accessing patients’ clinical records, medical devices distributed throughout the premises, and colleagues with whom they collaborate. In this paper, we present how autonomous agents provide capabilities of intelligence and proactivity to healthcare environments furnished with ubiquitous comp...

Ambient intelligence allows physical environments to become sensitive and responsive to the presence of people and objects. An environment endowed with ambient intelligence is able to analyse its contexts, adapt itself to the presence of people and objects residing in it, learn from their behaviour and recognise and express emotion. Ambient intelligence is realised via devices which blend into ...

Under Legg’s and Hutter’s formal measure [1], performance in easy environments counts more toward an agent’s intelligence than does performance in difficult environments. An alternate measure of intelligence is proposed based on a hierarchy of sets of increasingly difficult environments, in a reinforcement learning framework. An agent’s intelligence is measured as the ordinal of the most diffic...

This position paper claims that the combination of solutions to a finite collection of problem instances and an expansion capability of those solutions to similar problems is enough to achieve the artificial general intelligence comparable to the human intelligence. Learning takes place during expansion of existing solutions using various methods such as trial and error, generalization, case-ba...

In many AI settings an agent is comprised of both actionplanning and action-execution components. We examine the relationship between the precision of the execution component, the intelligence of the planning component, and the overall success of the agent. Our motivation lies in determining whether higher execution skill rewards more strategic playing. We present a computational billiards fram...

Agents are a central concept in Distributed Artificial Intelligence. What truly defines an agent and in what manner they are used is very broad. Distributed Problem Solving and Multiagent Systems are fields within Distributed Artificial Intelligence that use the agent concept quite extensively. This paper investigate the manner in which agents play a role in these two fields. An agent based app...