Helicopter hovering is an important challenge problem in the field of reinforcement learning. This paper considers several neuroevolutionary approaches to discovering robust cont...
Policy gradient approaches are a powerful instrument for learning how to interact with the environment. Existing approaches have focused on propositional and continuous domains on...
Through adjustable autonomy (AA), an agent can dynamically vary the degree to which it acts autonomously, allowing it to exploit human abilities to improve its performance, but wi...
Abstract—MapReduce is emerging as a generic parallel programming paradigm for large clusters of machines. This trend combined with the growing need to run machine learning (ML) a...
Amol Ghoting, Rajasekar Krishnamurthy, Edwin P. D....
Empirical work with "Belvedere," a software environment for the construction of diagrammatic representations of evidential relations, is summarized, leading to the hypot...