Research Interests
My research is on reinforcement learning, often from a theoretical perspective, as well as some other aspects of machine learning and statistics. I also enjoy dealing with challenging and novel applications.
Here I provide a brief summary of my research interests (divided to two broad categories of Theoretical Push and Application Pull) with pointers to some relevant publications.
Some papers might appear in more than one category. I may link to an extended version of a paper, if there was a severe page limitation for the official version. Earlier papers might not be mentioned if there is a more recent comprehensive paper. See Publications for an almost complete list.
Theoretical Push (this is a bit outdated!)
- Reinforcement Learning
- value function regularities [JMLR2016] [TAC2016] [NeurIPS2012] [NeurIPS2011] [NeurIPS2010] [ACC2009]
- policy regularities [TAC2016][NeurIPS2011]
- model regularities [NeurIPS2018][AISTATS2017]
- learning from demonstration [NeurIPS2013]
- computational speedup [AAAI2016]
- inverse optimal control [AAAI2015]
- model selection [MLJ2011]
- distributional RL [NeurIPS2019]
- Machine Learning
- non-i.i.d. processes and time series [NeurIPS2017] [JSPI2012]
- regularizer design [ICML2014]
- manifold learning [ICML2007]
- Intersection of Control Engineering and Machine Learning [ACC2016]
- Interaction of Learning and Evolution [TEC2010]
Application Pull
- PDE control (smart air conditioning systems) [CDC2016] [ACC2017][ICML2018]
- Fault detection/prognostics for time series [PHM2017][NeurIPS2017]
- Robotics (uncalibrated visual-servoing, behavior-based architectures) [ICRA2010] [ICRA2009] [IROS2007] [TEC2010]
- Hybrid vehicles energy management system [AAAI2016]