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 Social Work research there is a strong debate on the distinctiveness and methodological quality, and how to address the dilemma of rigour and practice relevance. Given the nature of Social Work the field has developed a characteristic research culture that puts emphasis on giving voice to service users and disseminating research knowledge in practice, especially in a stream of so called practice-based research. However, there is no consensus on how to best contribute to the practice of Social Work through research and at the same time producing rigourous scientific outcomes, resulting in methodological pluralism. Studying the perceptions of Social Work researchers on their role, the aims and values of Social Work research and their research approach, provides insight into the methodological pluralism of Social Work research. Thirty-four professors specialising in practice-based Social Work research participated in a Q methodology study. Q methodology combines qualitative and quantitative methods. It helped reveal and describe divergent views as well as consensus. The analysis led to the identification of three differing viewpoints on Social Work research, which have been given the following denominators: The Substantiator, The Change Agent and The Enlightener. The viewpoints provide researchers in the field of Social Work with a framework in which they can position themselves in the methodological pluralism. Researchers state that the viewpoints are helpful in clarifying perspectives on good research, facilitate the discourse on methodological choices to further develop and strengthen Social Work research as a scientific discipline
DOCUMENT
From the introduction: "There are two variants of fronto-temporal dementia: a behavioral variant (behavioral FTD, bvFTD, Neary et al. (1998)), which causes changes in behavior and personality but leaves syntax, phonology and semantics relatively intact, and a variant that causes impairments in the language processing system (Primary Progessive Aphasia, PPA (Gorno-Tempini et al., 2004). PPA can be subdivided into subtypes fluent (fluent but empty speech, comprehension of word meaning is affected / `semantic dementia') and non-fluent (agrammatism, hesitant or labored speech, word finding problems). Some identify logopenic aphasia as a FTD-variant: fluent aphasia with anomia but intact object recognition and underlying word meaning."
MULTIFILE
