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
In the fall of 1999, we started, the Integrated Product Development- Collaborative Engineering ( IPD-CE) project as a first pilot. We experimented with modern communication technology in order to find useful tools for facilitating the cooperative work and the contacts of all the participants. Teams have been formed with engineering students from Lehigh University in the US, the Fontys University in Eindhoven, The Netherlands and from the Otto-von-Guericke University in Magdeburg, Germany. In the fall of 2000 we continued and also cooperated with the Finnish Oulu Polytechnic. It turned out that group cohesion stayed low (students did not meet in real life), and that Internet is not mature enough yet for desktop video conferencing. Chatting and email were in these projects by far the most important communication media. We also found out that the use of a Computer Support for Cooperative Work (CSCW) server is a possibility for information interchange. The server can also be used as an electronic project archive. Points to optimise are: 1. We didn't fully match the complete assignments of the groups; 2. We allowed the groups to divide the work in such parts that those were developed and prototyped almost locally; 3. We haven't guided the fall 2000 teams strong enough along our learning curve and experiences from previous groups. 4. We didn't stick strong enough to the, by the groups developed, protocols for email and chat sessions. 5. We should facilitate video conferencing via V-span during the project to enhance the group performance and commitment.
Purpose: This paper aims to define the influence of the physical and social dimensions of the work environment on knowledge productivity of academics in Dutch Universities of Applied Sciences.Design/methodology/approach: Literature review; a multiple case study based on literature review (6 cases); a survey (n=188).Findings: Knowledge workers share two basic needs: their productivity requires isolation (internalization of knowledge) and interaction (externalization of knowledge), supported by different spatial concepts. None of the work environments involved in the study adequately support all of the phases in the knowledge development process adequately. Collective productivity is primarily determined by the physical dimension of the workplace; whereas the social dimension is crucial for personal productivity. Social interaction has a stronger effect than distraction; and the layout has a stronger effect than comfort.Conclusions - A high performance workplace supports both externalization and internalization of knowledge, allowing group members to collaborate and communicate according to need. More traditional work environments support internalization; innovative workplace designs (the office as meeting place) are more suited to support interaction and collaboration. Discover why freedom of choice is the key.Recommendations - Academics should be allowed to choose as to how, where and when they work and involved during the development of new concepts.Paper type: Research paper
MULTIFILE
The PANTOUR consortium builds on previous knowledge and tools produced by the Blueprint for Sectoral Skills project/NTG Alliance and will develop new tools and methodology to address strategic and sustainable approaches and cooperation between vocational education, training, higher education, enterprises of the tourism sector, looking to boost innovation in Europe (in tourism, leisure and hospitality).Societal IssueThe aim of this project is to map and bridge the existing skills gaps in Green, Social and Digital skills of workforce in tourism, leisure and hospitality.Benefit to societyMaking lifelong learning and mobility a reality, developing innovative learning solutions and promoting inclusiveness and access to education. Promoting active citizenship, building equal opportunities and addressing gender equality, diversity and inclusiveness in targeted actions.The consortium aims especially at designing innovative and cooperative solutions to address skills needs in the tourism ecosystem, with the development of outputs such as: the Sectoral Skills Intelligence Monitor, the Tourism Skills Lab, Resource Books for Trainers, the implementation of the National Skills Groups, a Skills Strategy Plan for 2026-2036, among others. With the exploitation of its outputs, PANTOUR seeks to benefit job seekers, unemployed and employed workers from the industry, employers, SMEs and micro entrepreneurs, dedicating a special attention in reskilling and upskilling the workforce on future skills needs in digital, green and social skills.The number of people benefiting from this proposal will be over 10 million that work across the tourism and leisure sector in Europe.The consortium is a multi-disciplinary partnership which comprises 13 European partners: Industry Partners and Tourism Sector Representatives, Universities and Transnational partners. Project lead is CEHAT (Spain). The other partners are GESTLABOR (Spain), Turismo de Portugal (Portugal), Zangador Research Institute (Bulgaria), Technological University Dublin (Ireland), Federturismo Confindustria (Italy), VIMOSZ (Hungary), European Tourism Association ETOA (Transnational), Satakunta University of Applied Sciences (Finland), Ruraltour (Transnational), Landurlaub (Germany), University of the Aegan (Greece).
PUBLIC PLAY SPACE promotes innovative and creative practices for the co-design of inclusive, cohesive and sustainable public spaces, through the use of games and digital technologies, in a transnational and European perspective, fostering the process of placemaking.Participation of citizens in the design of the public space is recognized as fundamental to build inclusive, cohesive and sustainable public space. As local governments grow more and more interested in civic participation, it becomes important to explore available methodologies addressing challenges related with participatory processes. Games have been proposed since the 1960s as a means of facilitating participatory processes by enabling cooperative environments to shape and support citizens’ interaction. The change led by Information and Communication technologies opens the debate on how advanced technologies, from video games to Virtual and Augmented Reality can help to open the process of co-creation to new audiences, enhancing citizen participation, both with respect to the design and space usage. PUBLIC PLAY SPACE aims to explore the process of development and use of innovative video-games for public space co-design through a wide range of actions targeted at education, knowledge production, debate rising and audience development; it will focus on the following actions:- On-line platform development;- State of the art book development;- 3 Creative & Capacity building workshops on advanced video-games co-development;- 3 Open-Game Events / Public space co-creation workshops with citizens (T: Neighbourhood associations, young people, citizens);- A Co-created touring exhibition on Games for placemaking, taking place in 6 cities;- 1 symposium on games for co-design;- Public Play Space experience book.
