- Diploma in Electronic and Computer Engineering, Technical University of Crete, 2001.
- M.S in Production Engineering and Management, Technical University of Crete, 2004.
- M.S. in Computer Science and Engineering, University of Minnesota, 2007.
- M.S. in Electrical Engineering, University of Southern California, 2010.
- Ph.D in Computer Science, University of Southern California, 2011.
Evangelos Theodorou earned his Diploma in Electronic and Computer Engineering from the Technical University of Crete (TUC), Greece in 2001. He has also received a MSc in Production Engineering from TUC in 2003, a MSc in Computer Science and Engineering from University of Minnesota in spring of 2007 and a MSc in Electrical Engineering on dynamics and controls from the University of Southern California(USC) in Spring 2010. In May of 2011 he graduated with his PhD, in Computer Science at USC. After his PhD, he became a Postdoctoral Research Associate with the department of Computer Science and Engineering, University of Washington, Seattle. In July 2013 he joined the faculty of the school of Aerospace Engineering at Georgia Institute of Technology as Assistant Professor. His theoretical research spans the areas of control theory, machine learning, information theory and statistical physics. Applications involve autonomous planning and control in robotics and aerospace systems, bio-inspired control and design.
- Nonlinear Stochastic Optimal Control
- Machine Learning and Reinforcement Learning
- Statistical Mechanics, Information Theory and Connections to Control Theory.
- Nonlinear State Estimation and Signal Processing
- Adaptive, Nonlinear and Model Predictive Control.
Honors and Distinctions
- Best research assistant fellow in Computer Science USC 2010.
- USC Myronis Fellowship 2009.
- E. Theodorou, K. Dvijotham and E. Todorov. Nonlinear Time Varying Policy Gradients. To appear in Control Decision Conference 2013,
- K. Dvijotham,E. Theodorou, E. Todorov and Maryam Fazel. Convexity of Optimal Control Design. To appear in Control Decision Conference 2013,
- E. Theodorou, K. Dvijotham and E. Todorov. From Information theoretic dualities to Path Integral and Kullback Leibler control: Continuous and Discrete Time Formulations. In 16th Yale workshop on Learning and Adaptive Systems, 2013.
- E. Theodorou and E. Todorov. Relative Entropy Free Energy Dualities: Connection to Path Integral and KL control. 51st IEEE Control Decision Conference (CDC), 2012.
- F. Stulp, E. Theodorou and S. Schaal. Reinforcement Learning With Sequence of Motion Primitives for Robust Manipulation. IEEE TRANSACTIONS ON ROBOTICS, 28(6):1360 -1370, 2012. King-Sun Fu Best Paper Award 2012.
- E. Theodorou, J. Buchli, and S. Schaal (2010). A Generalized Path Integral Control Approach to Reinforcement Learning. JOURNAL OF MACHINE LEARNING RESEARCH, 11, pp.3137-3181.