We consider the task of reinforcement learning in an environment in which rare significant events occur independently of the actions selected by the controlling agent. If these ev...
We describe an approach to building integrated performance support systems by using model-based task tracking to link performance support tools to video-based organizational memor...
Christopher R. Johnson, Lawrence Birnbaum, Ray Bar...
Due to its occurrence in engineering domains and implications for natural learning, the problem of utilizing unlabeled data is attracting increasing attention in machine learning....
Impact analysis, determining when a change in one part of a program affects other parts of the program, is timeconsuming and problematic. Impact analysis is rarely used to predict...
Abstract Self-healing, i.e. the capability of a system to autonomously detect failures and recover from them, is a very attractive property that may enable large-scale software sys...