Human-in-the-Loop Reinforcement Learning for Real-World Robotics Applications

The Army Research Laboratory (ARL) has a research opportunity available in the research and development of human-in-the-loop reinforcement learning (RL) systems. Specifically, ARL is looking for an outstanding individual to advance development of human-in-the-loop deep reinforcement learning techniques for solving complex, real world robotics applications (such as obstacle avoidance, path navigation and grasping tasks). A successful candidate will have expertise in one or more of the following areas: Robotics, statistical classification and machine learning methods, deep reinforcement learning, optimal control, experimental design, and computer programming. Emphasis will be on translational research and technology development that will leverage current internal ARL research on human-in-the-loop RL. Candidate will support the short-term goal of developing a working proof-of-concept system that demonstrates the viability human-in-the-loop RL control in robotic environments. The candidate will perform system development, conduct experiments, publish papers, and integrate ideas and methods with the ongoing efforts of a multidisciplinary research team. This opportunity is part of the Army Research Laboratory Research Associateship Program (ARL-RAP), which 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.