Raymond Chua

Last updated 25 Feb 2026.

I recently defended my PhD in Computer Science at McGill University, conducted at Mila – Quebec Artificial Intelligence Institute, under the supervision of Doina Precup and Blake Richards. My research bridges reinforcement learning and computational neuroscience, investigating how principles such as predictive representations and memory consolidation can inform the design of adaptive, continually learning AI systems.

My doctoral work addressed the plasticity–stability dilemma in reinforcement learning through structured predictive representations and multi-timescale learning mechanisms, demonstrating how biologically inspired approaches can reduce interference while preserving adaptability.

Building on this foundation, I am increasingly interested in mechanistic interpretability — using tools inspired by neuroscience, such as representation similarity analysis and cross-attention probing, to understand how predictive representations (e.g., successor features) encode and transform information over time. I am particularly motivated by questions at the intersection of continual learning, foundation models, and embodied decision-making systems.

Beyond research, I’m passionate about improving AI capabilities through academic–industry partnerships, where I mentor students from McGill, UdeM, and Mila as they tackle real-world challenges with companies seeking to integrate machine learning into their products and pipelines. During my free time, I enjoy pushing both my intellectual and physical abilities through triathlon, which continues to teach me about endurance, balance, and growth.