Machine Learning for State Estimation and Decision Propagation

The Army Research Laboratory Research Associateship Program (ARL-RAP) offers a postdoctoral fellowship position in Machine Learning for State Estimation and Decision Propagation. This opportunity focuses on Network of Networks to enable novel methods for agent learning, adaptation, and model distribution in highly heterogeneous environments where humans are coupled to machine decision agents. The research will develop novel theories, experiments, and hardware solutions to enable hierarchical and deeply integrated Human-in-the-Loop (HIL) reinforcement, transfer learning for heterogeneous agents, extending methods from simulation demonstrations to hardware in the loop mixed systems building on advances from projects like Google DeepMind. The selected postdoctoral fellow will lead their own research efforts within a highly collaborative research group, with expectations to publish first author efforts in peer reviewed literature and contribute to diverse research areas. The work involves a mix of skill sets including deep understanding of machine learning, transfer and reinforcement learning techniques, developing theories supporting multi-agent learning, and transfer of learned behavior across heterogeneous agents. Research will be conducted using Python, Linux, ROS, Matlab, and C/C++. The 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. The program supports Army forces in meeting future operational needs by pursuing scientific research and technological developments in diverse fields including applied mathematics, digital/optical signal processing, nanotechnology, material science, computational and information sciences, among others. This position is within the Sensors and Electron Devices Directorate (SEDD), the Army's principal center for research and development in the exploration and exploitation of the electromagnetic spectrum. The advisor for this opportunity is Joseph Conroy.