Key to reinforcement learning in multi-agent systems is the ability to exploit the fact that agents only directly influence only a small subset of the other agents. Such loose couplings are often modelled using a graphical model: a coordination graph. Finding an (approximately) optimal joint action for a given coordination graph is therefore a central subroutine in cooperative multi-agent reinforcement learning (MARL). Much research in MARL focuses on how to gradually update the parameters of the coordination graph, whilst leaving the solving of the coordination graph up to a known typically exact and generic subroutine. However, exact methods { e.g., Variable Elimination { do not scale well, and generic methods do not exploit the MARL setting of gradually updating a coordination graph and recomputing the joint action to select. In this paper, we examine what happens if we use a heuristic method, i.e., local search, to select joint actions in MARL, and whether we can use outcome of this local search from a previous time-step to speed up and improve local search. We show empirically that by using local search, we can scale up to many agents and complex coordination graphs, and that by reusing joint actions from the previous time-step to initialise local search, we can both improve the quality of the joint actions found and the speed with which these joint actions are found.
LINK
Artificially intelligent agents increasingly collaborate with humans in human-agent teams. Timely proactive sharing of relevant information within the team contributes to the overall team performance. This paper presents a machine learning approach to proactive communication in AI-agents using contextual factors. Proactive communication was learned in two consecutive experimental steps: (a) multi-agent team simulations to learn effective communicative behaviors, and (b) human-agent team experiments to refine communication suitable for a human team member. Results consist of proactive communication policies for communicating both beliefs and goals within human-agent teams. Agents learned to use minimal communication to improve team performance in simulation, while they learned more specific socially desirable behaviors in the human-agent team experiment
DOCUMENT
This paper describes an agent-based software infrastructure for agile industrial production. This production is done on special devices called equiplets. A grid of these equiplets connected by a fast network is capable of producing a variety of different products in parallel. The multi-agent-based underlying systems uses two kinds of agents: an agent representing the product and an agent representing the equiplet.
MULTIFILE
This chapter presents the currently not established and identifies design requirements for new systems to address this challenge and provide directions for possible improvement. As a result, this chapter introduces the concept of SamenMarkt®, a participatory system in which multi-agent system technology enables distributed price negotiation, distribution and communication between producers, retailers and consumers.
LINK
Author supplied: The production system described in this paper in an implementation of an agile agent-based production system. This system is designed to meet the requirements of modern production, where short time to market, requirementdriven production and low cost small quantity production are important issues. The production is done on special devices called equiplets. A grid of these equiplets connected by a fast network is capable of producing a variety of different products in parallel. The multi-agent-based software infrastructure is responsible for the agile manufacturing. A product agent is responsible for the production of a single product and equiplet agents will perform the production steps to assemble the product. This paper describes this multiagent-based production system with the focus on the product agent. Presented at EUMAS 2013 ( 11th European Workshop on Multi-Agent Systems) , At Toulouse.
DOCUMENT
Author supplied: The production system described in this paper in an im- plementation of an agile agent-based production system. This system is designed to meet the requirements of modern production, where short time to market, requirement-driven production and low cost small quan- tity production are important issues. The production is done on special devices called equiplets. A grid of these equiplets connected by a fast network is capable of producing a variety of diverent products in parallel. The multi-agent-based software infrastructure is responsible for the agile manufacturing. A product agent is responsible for the production of a single product and equiplet agents will perform the production steps to assemble the product. This paper describes this multiagent-based production system with the focus on the product agent.
DOCUMENT
Athor supplied : "This paper describes an agent-based architecture for domotics. This architecture is based on requirements about expandability and hardware independence. The heart of the system is a multi-agent system. This system is distributed over several platforms to open the possibility to tie the agents directly to the actuators, sensors and devices involved. This way a level of abstraction is created and all intelligence of the system as a whole is related to the agents involved. A proof of concept has been built and functions as expected. By implementing real and simulated devices and an easy to use graphical interface, all kind of compositions can be studied using this platform."
DOCUMENT
Presented at the 11th International Conference on ICT in Education, Research and Industrial Applications: Integration, Harmonization and Knowledge Transfer Lviv, Ukraine, May 14-16, 2015. Author supplied: Abstract. User requirements and low-cost small quantity production are new challenges for the modern manufacturing industry. This means that small batch sizes or even the manufacturing of one single product should be affordable. To make such a system cost-effective it should be capable to use the available production resources for many different products in parallel. This paper gives a description of the requirements and architecture of an end-user driven production system. The end-user communicates with the production system by a web interface, so this manufacturing system can be characterized in terms of cloud comput- ing as the implementation of manufacturing as a service, abbreviated to MaaS.
DOCUMENT
Om veel leerplezier mogelijk te maken is in september 2004 het Open Space Atelier van start gegaan, waarin door studenten, docenten en hun kinderen vrij gewerkt en met elkaar gesproken kan worden over ons boeiende vak: het onderwijs. Er is geen agenda of programma. De gebeurtenissen worden door de inbreng van de aanwezigen bepaald. In het Lectoraat Vernieuwende Opleidingsmethodiek en -didactiek onderzoeken we met lector Hans Jansen manieren van Levend Leren (in het kerstboekje dat Jan Brandsma ons cadeau deed, is over Levend Leren al veel te lezen: leren mag spannend, uitdagend en geïnspireerd als het leven zelf zijn). Deze onderzoeken verlopen op verschillende wijze: literatuurstudie, observatie en het toetsen van denkbeelden en theorie aan de praktijk. Een van de wegen om Levend Leren vorm te geven is het onderzoek naar de weg van Teacher-Directed Learning naar Self-Directed Learning en Free Agent Learning. Bij onze kenniskringdagen werken we met een open space aanpak. Dan verkennen we gezamenlijk creatieve en inspirerende wegen in ons eigen leerlandschap.
DOCUMENT
This chapter gives an overview on the Healthy Ageing research portfolio of the research group Lifelong Learning in Music (Hanze University of Applied Sciences Groningen, the Netherlands). Lifelong learning enables musicians to respond to the continuously changing context in which they are working nowadays, and ageing is one of the major societal changes for many western societies in the 21st century. Musicians are asked by society to contribute to healthy ageing processes, and such a contribution in turn generates possibilities for innovative musical practices with the elderly. We present a three-layered model to look at such innovative practices, which places the musical practice itself in the context of communicative characteristics of working with elderly people and in broader societal and institutional contexts. We then outline four concrete research projects: learning to play an instrument at an elderly age, creative music workshops for elderly in residential home settings, the competencies of creative music workshop leaders working with frail elderly people, and musical work with severely ill elderly people in hospitals. We describe some background values and methodological notions behind our work, and finish the article with a more extensive description of our project on Music and Dementia.
DOCUMENT
