Concurrent Markov Decision Processes for Robust Robot Team Learning under Uncertainty

For robots to become a more common fixture in private and public industries, they must exhibit compliant individual and social learning. To achieve social compliance, while maintaining individual performance, robots must represent knowledge accurately in both certain and uncertain environments. Robots also need to quantify effective decision making both when isolated and when teamed with peer robots and humans. Thus, this thesis considers improvements to the Concurrent Individual and Social Learning (CISL) approach [30, 31], and addresses all of the above problems by exploring three subjects: learning problem representation using Markov Decision Processes (MDPs) [17], state uncertainty and state estimation [18], and advice sharing from both robot and human advisors [17, 19].M.A.S