Reinforcement Learning Under Epistemic Uncertainty: From Markov Models to Evidential Decision Processes
Why Go Beyond Classical HMM/MDP?
Research project pages — see status on each entry or on the Research page.
Why Go Beyond Classical HMM/MDP?
Intelligence does not scale linearly with compute. It reorganizes under constraint.
PhD track: formal foundations and engineering of safe hierarchical multi-agent RL for maintenance-and-repair decision support under uncer...
Currently suspended due my own projects. AI-based library to work with extremely large graphs.
Utilizing the Dempster–Shafer Theory for Condition Diagnosis of Continuous Casting Machines.