Comanici Gheorghe






  School of Computer Science, McGill University

   3480 University, Montréal, Québec

   H3A 2A7

   e-mail: gcoman [at] cs [dot] mcgill [dot] ca











































































About me:


My name is Gheorghe Comanici and I have recently finished work towards a PhD degree in Artificial Intelligence (AI) at McGill UniversityI am a proud citizen of Canada since 2006, but also fortunate to be raised in the midst of nature's beauty: Bistrita, Romania. I've lived there until 2002, when I was plunged in a culture amalgam called Montréal. For the last 8 years I have been part of the Reasoning and Learning Lab, a research group that works on applications and theory of machine learning techniques. For my post-graduate degree, I studied theoretical properties of mathematical frameworks for sequential decision-making. During the time spent completing my degree I was also actively involved in many teaching opportunities in the field of computer science. I have been a teaching assistant from 2008 to 2013 and part of the teaching staff at McGill for the last four years. I have devoted the time I spent at McGill University both for research and for teaching, which has always been something that I had great interest into. The School of Computer Science has been great environment for building my teaching skills, as I had the opportunity both to assist some great teachers in the department and to be in sole charge of preparing introductory courses in programming.

I believe that teaching at different educational levels is important for building better approaches when dealing with students. My personal experience from tutoring family members and friends are proof to that. Another example is my participation in assisting students with homework assignments, both in primary and secondary levels, at Tyndale St-Georges Community Centre. Moreover, I have worked with Kids Code Jeunesse, a non-profit organization for promotion of computing education throughout Canada, both as a volunteer teacher and as part of their Education Advisory Committee. During the same time, I have taken a number of courses in the Faculty of Education towards a degree in High-School instruction of mathematics. I have acquired a lot of interesting and useful ideas and practices which are necessary for teaching diverse groups of students and for the promotion of strong critical thinking skills.

My teaching duties at McGill University include:



Research:

My research interests revolve around Probabilistic Systems for Artificial Intelligence Systems; lately I have been mostly working on computational aspects of bisimulation metrics for state space abstraction for Markov Decision Process. I also find myself working on Hierarchical Reinforcement Learning, Temporal Abstraction, Spectral Learning and other Machine Learning topics. In my spare time I will be solving interesting problems on Data Structures, Statistics, Probability or Measure Theory. My ultimate goal is to contribute to the advancement of lifelong learning machines.




Find below a poster I have prepared to showcase my work and that of fellow members of the RL Lab. 



PUBLICATIONS:


  1. • Comanici, Gheorghe; Precup, Doina and Panangaden, Prakash. Basis refinement strategies for linear value function approximation. NIPS 2015 [paper]


  2. • Ruan, Sherry Shanshan; Comanici, Gheorghe; Panangaden, Prakash and Precup, Doina. Representation Discovery for MDPs using Bisimulation Metrics. 29th AAAI Conference, 2015 [paper]


  1. • Comanici, Gheorghe; Panangaden, Prakash and Precup, Doina. On-the-Fly Algorithms for Bisimulation Metrics. 9th International Conference on Quantitative Evaluation of SysTems (QEST), 2012 [paper] 


  2. • Paduraru, Cosmin; Precup, Doina; Pineau, Joelle and Comanici, Gheorghe. A Study of Off-Policy Learning in Computational Sustainability. Proceedings of the 9th European Workshop on Reinforcement Learning, 2012 [paper] 


  3. • Comanici, Gheorghe and Precup, Doina. Basis Function Construction using Spectral Clustering and Bisimulation Metrics. Lecture Notes in Computer Science, Volume 7113, 2012 [paper] 


  4. • Comanici, Gheorghe and Precup, Doina. Basis Function Construction using Spectral Clustering and Bisimulation Metrics. The 25th AAAI Conference, 2011 [paper]


  5. • Comanici, Gheorghe and Precup, Doina. Basis Function Construction using Spectral Clustering and Bisimulation Metrics (Extended Abstract). The 10th International Conference on Autonomous Agents and Multiagent Systems, 2011 [paper][poster] (presentation on the topic: [slides])


  6. • Comanici, Gheorghe. Optimal Time Scales for Reinforcement Learning Behaviour Strategies. Master Thesis, McGill University, 2010 [paper] (presentations on the topic: [slides1] [slides2] [poster])


  7. • Comanici, Gheorghe and Precup, Doina. Optimal Policy Switching Algorithms for Reinforcement Learning. The 9th International Conference on Autonomous Agents and Multiagent Systems, 2010 [paper][poster][slides]






  1. Photography is one of my passions. A 2D grid of pixels is just enough information for the human mind to both capture a moment of “open shutter” and ignite imagination on a lifetime span. On the side you will enjoy some pictures that I am proud of.