The design ideal of the invisible computer, prevalent in the vision of ambient intelligence (AmI), has led to a number of interaction challenges. The complex nature of AmI environm...
Jo Vermeulen, Jonathan Slenders, Kris Luyten, Kari...
Reinforcement learning algorithms that use eligibility traces, such as Sarsa(λ), have been empirically shown to be effective in learning good estimated-state-based policies in pa...
We consider the setting of multiple collaborative agents trying to complete a set of tasks as assigned by a centralized controller. We propose a scalable method called“Assignmen...
This paper reports on a novel decentralised technique for planning agent schedules in dynamic task allocation problems. Specifically, we use a Markov game formulation of these pr...
Archie C. Chapman, Rosa Anna Micillo, Ramachandra ...
Real-time strategy games share many aspects with real situations in domains such as battle planning, air traffic control, and emergency response team management which makes them a...
Ronald A. Metoyer, Simone Stumpf, Christoph Neuman...