Reinforcement Learning for Information Asset Valuation and Selection

This research opportunity is to develop a novel method for information asset selection, filtering, prioritization. Specifically, this opportunity will develop and validate a concept and approach for selecting the most relevant and valuable information for presentation and sharing from a collection of streaming sensor data. This project focuses on utilizing state-of-the-art reinforcement algorithms to 1) dynamically learn from multi-agent actions and context, 2) evaluate the environment and uncertainty, and 3) optimize information sharing and consumption. The key technical areas in this project include reinforcement learning, graphical neural network, information theory, probability, and stochastic process. The Army Research Laboratory Research Associateship Program (ARL-RAP) is designed to significantly increase the involvement of creative and highly trained scientists and engineers from academia and industry in scientific and technical areas of interest and relevance to the Army. This opportunity is within the Computational and Information Sciences Directorate (CISD), which conducts research in a variety of disciplines relevant to achieving and implementing the so-called digital battlefield.