ASR Research Group Banner

Dr M Smyrnakis
Research Fellow

Dr M SmyrnakisDepartment of Automatic Control & Systems Engineering
Rm F41, SCentRo (Sheffield Centre for Robotics), Pam Liversidge Building
University of Sheffield
Sheffield
S1 3JD
Tel: (+44) (0)114 222 6082
Email: m.smyrnakis @ sheffield.ac.uk

Biography

Dr Michalis Smyrnakis is a Research Fellow in the Department of Automatic Control & Systems Engineering (ACSE), University of Sheffield. His current work focuses on distributed sensing, control, and decision making. Michalis also has research interests in Game Theory, Multi-Agent Learning, and Neural Networks.

Dr Smyrnakis received his Bachelor's degree in Statistics from Athens University of Economics and Business in 2005, and his Master's degree in Pattern Analysis and Neural Networks from Aston University in 2006. He obtained his PhD in 2010 from the Department of Mathematics, University of Bristol. He then moved to the Complexity Group at the School of Physics and Astronomy, University of Manchester, where he worked as a Research Associate from 2010-2013.

In 2013 Michalis joined the Autonomous Systems and Robotics Research Group, University of Sheffield, to work on the EPSRC project Distributed Sensing, Control and Decision Making.

Research interests

Dr Smyrnakis's research interests include:

  • Game Theory;
  • Multi-Agent Learning;
  • Distributed Control;
  • Bayesian Optimal Filtering;
  • Monte-Carlo Methods;
  • Neural Networks.

Book chapters

  • M. Smyrnakis and T. Galla. Decentralized optimisation of resources in disaster management. To appear in City evacuations: an interdisciplinary approach. Editor John Preston
  • M. Smyrnakis. Robustness of fictitious play in a resource allocation game. To appear in Applications of Mathematics and Informatics in Science and Engineering. Editor Nicholas J. Daras

Journal articles

  • M. Smyrnakis and T. Galla. Effects of communication and utility-based decision making in a simple model of evacuation. The European Physical Journal B 85, no. 11 (2012): 1-9
  • M. Smyrnakis and D. Leslie. Dynamic opponents modelling in Fictitious play. The Computer Journal 53, no. 9 (2010): 1344-1359.
  • M. Smyrnakis and D. Leslie. Adaptive forgetting factor fictitious play. (Under submission)

Conference papers (peer reviewed)

  • M. Smyrnakis and S. Veres. Coordination of control in robot teams using game-theoretic learning. To appear in Proceedings of the 19th World Congress of the International Federation of Automatic Control.
  • M. Smyrnakis and D. Leslie. Convergence of probability collectives with adaptive temperature parameters. Proceedings of the 4th international conference on Learning and intelligent optimisation, Venice, Italy 2010. In Learning and Intelligent Optimization, pp. 200-203. Springer Berlin Heidelberg, 2010.
  • M. Smyrnakis and D. Leslie. Sequentially updated probability collectives. Proceedings of the 48th IEEE Conference on Decision and Control, 2009 pp. 5774-5779.
  • M. Smyrnakis and D. Leslie. Stochastic Fictitious Play using Particle Filters to update the beliefs of opponents’ strategies. In Proceedings of the First International Workshop on Optimisation in Multi-Agent Systems (OPTMAS) at the Seventh International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2008). 2008.
  • M. Smyrnakis and D. Evans. Classifying Ischemic Events Using a Bayesian Inference Multilayer Perceptron and Input Variable Evaluation Using Automatic Relevance Determination. In Computers in Cardiology, 2007, pp. 305-308. IEEE, 2007.

Back to top