Agents Leveraging Learning for Intelligent Engagement with Soldiers (A.L.L.I.E.S.)

The Army Research Laboratory Research Associateship Program (ARL-RAP) offers a research opportunity focused on the A.L.L.I.E.S. project. The primary objective is to develop, test, and validate techniques for training artificial intelligence (AI) agents to work flexibly and efficiently alongside other AI agents and humans/Soldiers to accomplish tasks, goals, and the overall mission in dynamic multi-domain operations (MDO). This project specifically focuses on utilizing state-of-the-art multi-agent reinforcement learning (MARL) algorithms combined with Human-in-the-Loop (HitL) approaches to find a methodology for training AI agents to rapidly and flexibly adapt to, or learn from partners (human or agent) actions to complete tasks in novel situations and environments. The program 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 research is conducted through the Computational and Information Sciences Directorate (CISD), which focuses on communications, atmospheric modeling, battlefield visualization, and computing.