Ian Gemp
From Optimization to Equilibration: Understanding an Emerging Paradigm in Artificial Intelligence and Machine Learning
Students and collaborators
Research is a collective trajectory.
The work represented here was shaped by generations of students, collaborators, interns, and research communities. The alumni list records PhD dissertations rather than freezing people at an inevitably outdated job title.
Thomas Boucher
Transfer Learning with Mixtures of Manifolds
Clemens Rosenbaum
Dynamic Composition of Functions for Modular Learning
Clifton Carey
Graph Construction for Manifold Discovery
Bo Liu
First-Order Optimization Methods for Reinforcement Learning
Chang Wang
A Geometric Framework for Transfer Learning using Manifold Alignment
Jeff Johns
Basis Construction and Utilization in Markov Decision Processes using Graphs
Sarah Osentoski
Action-Based Representation Discovery in Markov Decision Processes
Mohammad Ghavamzadeh
Hierarchical Reinforcement Learning in Continuous State and Multiagent Environments
Khashayar Rohanimanesh
Concurrent Decision Making in Markov Decision Processes
Georgios Theocharous
Hierarchical Partially Observable Markov Decision Processes for Robot Navigation
Mentorship
From learning apprentices to research apprenticeships
Teaching, advising, and collaboration have been inseparable from the research itself: an intelligent theory grows through explanation, correction, and the transport of ideas between people and domains.