In this paper we introduce a novel interface for exploring dynamic equilibria using the metaphor of a traditional balance scale. Rather than comparing and identifying physical weig...
Active machine learning algorithms are used when large numbers of unlabeled examples are available and getting labels for them is costly (e.g. requiring consulting a human expert)...
— Sampling-based kinodynamic planners, such as the popular RRT algorithm, have been proposed as promising solutions to planning for systems with dynamics. Nevertheless, complex s...
In reinforcement learning problems it has been considered that neither exploitation nor exploration can be pursued exclusively without failing at the task. The optimal balance bet...
Energy expenditure has become a significant fraction of data center operating costs. Recently, “geographical load balancing” has been suggested to reduce energy cost by explo...
Zhenhua Liu, Minghong Lin, Adam Wierman, Steven H....