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
Research into the relationship between innovative physical learning environments (PLEs) and innovative psychosocial learning environments (PSLEs) indicates that it must be understood as a network of relationships between multiple psychosocial and physical aspects. Actors shape this network by attaching meanings to these aspects and their relationships in a continuous process of gaining and exchanging experiences. This study used a psychosocial-physical, relational approach for exploring teachers’ and students’ experiences with six innovative PLEs in a higher educational institute, with the application of a psychosocial-physical relationship (PPR) framework. This framework, which brings together the multitude of PLE and PSLE aspects, was used to map and analyse teachers’ and students’ experiences that were gathered in focus group interviews. The PPR framework proved useful in analysing the results and comparing them with previous research. Previously-identified relationships were confirmed, clarified, and nuanced. The results underline the importance of the attunement of system aspects to pedagogical and spatial changes, and of a psychosocial-physical relational approach in designing and implementing new learning environments, including the involvement of actors in the discourse within and between the different system levels. Interventions can be less invasive, resistance to processes could be reduced, and innovative PLEs could be used more effectively.
MULTIFILE
