Ph.D. in Robotics08/2008 to present
Carnegie Mellon University, Pittsburgh, PA, USA

M.Sc. in Robotics08/2008 to 07/2011
For completing the course, research, writing and speaking qualifiers of the Ph.D. in Robotics program.
Carnegie Mellon University, Pittsburgh, PA, USA

M.Sc. in Computer Science09/2006 to 08/2008
Thesis: Model-Based Bayesian Reinforcement Learning in Complex Domains.
McGill University, Montreal, Qc, Canada

B.A.Sc. in Computer Science09/2004 to 05/2006
Specialization in Software Engineering
Laval University, Quebec city, Qc, Canada

Technical Degree in Computer Science08/2001 to 05/2004
CEGEP Francois-Xavier-Garneau, Quebec city, Qc, Canada

• Investigated and developed several novel reduction-based approaches to imitation learning and structured prediction.
• Analyzed theoretical properties of such approaches, including regret and sample complexity.
• Implemented these approaches on two large imitation learning problems: a 3D kart racing video game and Super Mario Bros game.
• Implemented these approaches on two large computer vision applications: LADAR 3D point cloud classification and 3D surface layout estimation from a single camera image.
• Developed code for inverse kinematics control and autonomous balance control for a six-legged mining robot developed at the National Robotics Engineering Center (NREC).

• TA for the class: 16-899C Adaptive Control and Reinforcement Learning, taught by Drew Bagnell.
• Helped prepare homeworks and midterm exam.
• Graded homeworks, midterms and final class projects.
• Answered students' questions on the class material during weekly office hours.
• Maintained class website and message board for announcements, posting homeworks and class notes, and discussion.
• Gave class lecture on TD methods in RL.

• Investigated new approaches for model-based Bayesian reinforcement learning in partially observable, continuous and structured environments.
• Developed new efficient planning and inference algorithms for model-based Bayesian reinforcement learning in such domains.

• Investigated online search and approximation techniques for POMDPs.
• Developed a new online search algorithm to solve POMDPs.
• Investigated the field of game theory and multiagent learning in incomplete information repeated games.
• Developed new algorithms for equilibrium learning in incomplete information repeated games.

• Developed and implemented various search, planning and scheduling algorithms in the RobocupRescue environment, which is a real time, dynamic and partially observable multiagent disaster management problem.
• Implemented and compared the performances of different approximate POMDP solvers such as PBVI, Perseus, RTDP-BEL, QMDP and RTBSS in 2 standard benchmarks (Tag and Rock Sample).
• Investigated and developed new hybrid POMDP approaches combining offline and online computation with the RTBSS algorithm.

• Analysed and conceived manufacture management software, such as project, time sheet, expense and JIT inventory management modules.
• Programmed these modules using C#, ASP.NET and VB6.

• Analysed and conceived the career and placement service system.
• Programmed the system using VB6 and their website using HTML and Javascript

NSERC Canada Graduate Scholarship (CGS D)2008
Tenured at Carnegie Mellon University.

FQRNT Doctoral Research Scholarship2008
Not tenured.

Dr. and Mrs. Milton Leong Graduate Student Award2007
Tenured at McGill University.

McGill Graduate Studies Fellowship2007
Tenured at McGill University.

McGill Recruitment Excellence Fellowship2006
Tenured at McGill University.

FQRNT Master's Research Scholarship2006
Tenured at McGill University.

NSERC Postgraduate Scholarship (PGS M)2006
Tenured at McGill University.

NSERC Undergraduate Student Research Award2005
Tenured at Laval University.