I will be joining the School of Electrical Engineering and Computer Science (EECS) at the University of Ottawa in September 2025, where I will establish the Machine Intelligence and Robot Learning (MIRL) group. I am currently recruiting motivated Master’s and Ph.D. students interested in reinforcement learning (RL) with applications in robotics, automation, scientific discovery, and beyond.

My research centers on embodied AI—developing intelligent agents that interact with and learn from the physical world. I am particularly interested in how agents can learn efficiently and safely, and adapt to new or evolving conditions. My work spans goal-conditioned learning, observation-cost-sensitive decision-making, and learning from limited or imbalanced data, with a strong focus on real-world applicability.

Currently, I am a Staff Scientist at the National Research Council of Canada (NRC) and an Adjunct Professor in the Faculty of Computer Science at Dalhousie University. At the NRC, my work focuses on the development of RL for robotic control and AI for complex design problems where data is costly, limited, or high-stakes. This includes:

• Observation- and intervention-aware reinforcement learning
• Sim2real transfer and model-based control
• Deep learning from limited and imbalanced datasets

From 2016–2018, I was a Postdoctoral Fellow at the University of Alberta with the Alberta Machine Intelligence Institute (Amii), working with Dr. Osmar Zaïane on learning from rare and structured data. I also held a short-term research appointment at Dalhousie University with Dr. Luís Torgo on class imbalance and rare case learning.

I earned my Ph.D. in Computer Science from the University of Ottawa, where I was supervised by Dr. Nathalie Japkowicz and Dr. Christopher Drummon. My dissertation, A Framework for Manifold-Based Synthetic Oversampling, focused on developing techniques to improve learning from imbalanced data. I completed my Master’s at Carleton University under the supervision of Dr. John Oommen, with a thesis titled Modelling and Classifying Stochastically Episodic Events.

Research Interests

Reinforcement Learning (RL)

• Goal Conditioned RL, Model-Based RL, Safe RL, RL + Foundation Models
• Exploration, Sample Efficiency, Action Contingent Noiselessly Observerable MDPs, Sim2Real

Machine Learning (ML)

• Learning from Limited and Imbalanced Data
• Active Learning
• Explainable and Interpretable ML

Applications

• Robotics, Healthcare, Industrial Automation, AI for Science, Environment and Climate Change, Space