Raymond Chua

Last updated 16 Sep 2026.

Presenting our work on Fast & Slow Successor Features at ICML 2026 in Seoul.

I am an incoming Postdoctoral Research Scientist at Columbia University’s Zuckerman Institute and Center for Theoretical Neuroscience in New York City, USA 🇺🇸, where I will work with Prof. Ken Miller and Prof. Kimberly Stachenfeld.

My research sits at the intersection of machine learning, computational neuroscience, and NeuroAI. I study how principles of biological learning and memory — including predictive representations, synaptic consolidation, and learning across multiple timescales — can help us understand adaptive behavior in both artificial and biological systems. At Columbia, I will extend these ideas toward computational models of learning and decision-making in neuropsychiatric disorders, starting with depression.

Beyond research, I am passionate about building stronger connections between academia and industry through academic–industry partnerships, where I have mentored students from McGill, Université de Montréal, and Mila on real-world machine learning problems. Outside of research, I enjoy challenging myself through triathlon, which continues to teach me about endurance, balance, and growth.

news

Sep 01, 2026	I’m excited to share that I’ll be joining Columbia University’s Zuckerman Institute and Center for Theoretical Neuroscience as a postdoctoral researcher, working with Ken Miller and Kim Stachenfeld. My research will explore learning, memory, and decision-making at the intersection of computational neuroscience, reinforcement learning and NeuroAI.
Jul 06, 2026	Presented our work, “Balancing Plasticity and Stability with Fast and Slow Successor Features,” at International Conference on Machine Learning (ICML) in Seoul, South Korea! The work studies how learning across multiple timescales using a neuro-inspired synaptic consolidation mechanism can help RL agents retain useful predictive representations while adapting to continuously changing environments.
Jun 01, 2026	Joined Natural Intelligence in Frankfurt as a Research Scientist Intern, working on biologically inspired recurrent models for Reinforcement Learning.
May 30, 2026	Graduated with a PhD in Computer Science from McGill University and Mila, advised by Prof. Doina Precup and Prof. Blake Richards. My dissertation explored how principles inspired by biological learning and memory can be used to develop more adaptive Continual Reinforcement Learning systems. In particular, I studied predictive representations — Successor Representations and Successor Features — together with neuro-inspired synaptic consolidation mechanisms to better balance plasticity and stability in continually learning agents.
Apr 30, 2026	Our latest work (together with Doina Precup and Blake Richards) on continual reinforcement learning and biologically inspired memory systems, “Balancing Plasticity and Stability with Fast and Slow Successor Features,” has been accepted to International Conference on Machine Learning (ICML) 2026. See you in Seoul, Korea! 🇰🇷🧠🚀

selected publications

ICML

Balancing Plasticity and Stability with Fast and Slow Successor Features

Raymond Chua, Doina Precup, and Blake A. Richards

Proceedings of the 43rd International Conference on Machine Learning (ICML), 2026

Raymond Chua is the corresponding author. Blake A. Richards and Doina Precup are co-senior authors.

PDF Code Blog
NeurIPS

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments

Riley Simmons-Edler, Ryan P Badman, Felix Baastad Berg, and 5 more authors

Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS), 2025

This is my first collaboration work with members of Prof. Kanaka Rajan’s lab. Riley and Ryan are first authors, and Prof. Kanaka Rajan is the corresponding author.

PDF Blog
NeurIPS

Learning Successor Features the Simple Way

Raymond Chua, Arna Ghosh, Christos Kaplanis, and 2 more authors

Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS), 2024

Raymond Chua is the corresponding author. Blake A. Richards and Doina Precup are co-senior authors.

PDF Code Blog
Journal

Learning offline: memory replay in biological and artificial reinforcement learning

Emma L. Roscow, Raymond Chua, Rui Ponte Costa, and 2 more authors

Trends in Neurosciences, 2021

Abs PDF Blog

Learning to act in an environment to maximise rewards is among the brain’s key functions. This process has often been conceptualised within the framework of reinforcement learning, which has also gained prominence in machine learning and artificial intelligence (AI) as a way to optimise decision making. A common aspect of both biological and machine reinforcement learning is the reactivation of previously experienced episodes, referred to as replay. Replay is important for memory consolidation in biological neural networks and is key to stabilising learning in deep neural networks. Here, we review recent developments concerning the functional roles of replay in the fields of neuroscience and AI. Complementary progress suggests how replay might support learning processes, including generalisation and continual learning, affording opportunities to transfer knowledge across the two fields to advance the understanding of biological and artificial learning and memory.