Artificial Intelligence Lab
Machine Learning
| Overview |
|
Research in machine learning at Michigan encompasses supervised, unsupervised and reinforcement learning (RL). In RL we focus on building autonomous agents that can learn to act in complex, sequential and uncertain environments. In particular, a number of research projects derive from an interest in building long-lived and flexibly-competent agents rather than the more usual agents that perform one complex task repeatedly. How should the rewards, actions and states be defined for such a system? Other areas of interest in machine learning include: 1) the integration of multiple learning methods into the cognitive architecture Soar, 2) developing specialized reinforcement learning methods for adaptive treatment design, and 3) developing unsupervised semi-supervised and supervised learning for sensor placement and management as well as for information retrieval and natural language processing. |
|
Faculty Baveja, Satinder Singh Holland, John H. Laird, John E. Lee, Honglak Olson, Edwin Radev, Dragomir Scott, Clayton D Syed, Zeeshan H. Affiliated Faculty Murphy, Susan Related Labs, Centers, and Groups Center for the Study of Complex Systems Reinforcement Learning Group |
|