Raymond Chua

PhD @mcgillu and @Mila_Quebec. Into #AI 🤖 & #neuroscience 🧠. 🏊🏻🚴🏽‍♂️🏃🏻‍♂️🏕️ when away from 💻 .

[Raymond Chua @RaymondRChua]

Excited to share our new paper accepted at ICML 2026 with @tyrell_turing and Doina Precup!

🇰🇷 See you in Seoul.

A major challenge in continual reinforcement learning is balancing:
• plasticity (learning new things)
• stability (not forgetting old ones)

🧵

1/15

[Raymond Chua @RaymondRChua]

@AndrewLampinen This motivated our focus on preserving predictive representations across multiple timescales.

Paper: https://t.co/WaDGp7edj9
Tweet: https://t.co/jWWsokJigD

[Raymond Chua @RaymondRChua]

Excited to share our new paper accepted at ICML 2026 with @tyrell_turing and Doina Precup!

🇰🇷 See you in Seoul.

A major challenge in continual reinforcement learning is balancing:
• plasticity (learning new things)
• stability (not forgetting old ones)

🧵

1/15

[Raymond Chua @RaymondRChua]

@AndrewLampinen We found that under gradual non-stationarity, severe losses of plasticity were indeed much less apparent than in many task-switching settings. However, continual learning remained challenging because stability, and not plasticity, became the primary bottleneck.

[Raymond Chua @RaymondRChua]

Also, special thanks to @ckaplanis1 for sharing his expertise on synaptic consolidation throughout this project. Many of the ideas in this work benefited greatly from our discussions.

[Raymond Chua @RaymondRChua]

Excited to share our new paper accepted at ICML 2026 with @tyrell_turing and Doina Precup!

🇰🇷 See you in Seoul.

A major challenge in continual reinforcement learning is balancing:
• plasticity (learning new things)
• stability (not forgetting old ones)

🧵

1/15

[Raymond Chua @RaymondRChua]

Paper: https://t.co/WaDGp7edj9

Blog: https://t.co/1YTUel0gb3

Code:
MuJoCo / PyTorch: https://t.co/QGEhp25GPG

Four Rooms / Jax: https://t.co/b5JktzijOS

Looking forward to discussions at ICML 2026 in Seoul 🇰🇷

15/15

[Kempner Institute at Harvard University @KempnerInst]

📢 Applications for the Kempner AI Fellows Program are now open!

This program is designed for early-career researchers with strong technical preparation in modern machine learning. Applications close June 1st.

Learn more and apply 🔗 https://t.co/GtzKq9Yhpo

#KempnerInstitute