👋 Hi, I'm Henry (@mhngu23) — a passionate researcher in Artificial Intelligence and Machine Learning, with a particular focus on Reinforcement Learning.

My research focuses on advancing the frontiers of artificial intelligence, specifically on decision-making agents, to solve real-world problems and improve quality of life. I am driven by a commitment to impactful innovation, aiming to build intelligent systems that contribute to smarter, more sustainable communities. With a strong foundation in both theoretical and applied AI, I seek to bridge research and practice to create meaningful technological solutions that empower society.

🎓 I'm currently a PhD student at the A2i2 Lab, Deakin University, Australia.
🎓 I hold a Master of Artificial Intelligence from RMIT University, where I graduated with a GPA of 3.9/4.0.

📌 Google Scholar: https://scholar.google.com/citations?user=bU_mv-8AAAAJ&hl=en
🔗 LinkedIn: https://www.linkedin.com/in/minh-hoang-nguyen-521500175/
🧬 ORCID: https://orcid.org/0000-0002-8134-3341

🤝 I’m always open to collaboration and new opportunities in AI/ML research and applied projects. Let’s connect!

---

🚀 PhD Research Journey

• ICDM 2025
  Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting

  Authors: Hung Le, Sherif Abbas, Minh Hoang Nguyen, Van Dai Do, Huu Hiep Nguyen, Dung Nguyen

• ECAI 2025
  Cross-Domain Offline Reinforcement Learning with Nearest-Neighbor Guided Diffusion Model

  Authors: Linh Le Pham Van, Minh Hoang Nguyen, Duc Kieu, Hung Le, Hung The Tran, Sunil Gupta

• ECML/PKDD 2025
  Hybrid Cross-domain Robust Reinforcement Learning

  Authors: Linh Le Pham Van, Minh Hoang Nguyen, Hung Le, Hung Tran The, Sunil Gupta

• IJCAI 2025
  Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer

  Git Repo

  Authors: Minh Hoang Nguyen, Linh Le Pham Van, Thommen George Karimpanal, Sunil Gupta, Hung Le

• ECML/PKDD 2024
  Variable-Agnostic Causal Exploration for Reinforcement Learning

  Git Repo

  Authors: Minh Hoang Nguyen, Hung Le, Svetha Venkatesh

• AAMAS 2024 Tutorial
  Reinforcement Learning Exploration via Memory

  Git Repo

  Authors: Hung Le, Minh Hoang Nguyen, Van Dai Do

---

📄 Other Publications

• ACSW 2023
  Rug-pull Malicious Token Detection on Blockchain Using Supervised Learning with Feature Engineering

  Author: Minh Hoang Nguyen, Phuong Duy Huynh, Son Hoang Dau, Xiaodong Li

---

🧠 Study Suite

A curated set of personal repositories focused on mastering core AI/ML disciplines through hands-on implementation and experimentation.

• ai-architectures-from-scratch

  🔍 Focus: Fundamental understanding of deep nets and their mechanics.

• rl-study-suite

  🎓 Focus: Policy gradients, value-based methods, actor-critic methods.

• timeseries-study-suite

  📈 Focus: Classical & neural forecasting models, evaluation, visualization.

---

📖 Current Reading

• llm-reasoning-papers

  🤖 Focus: Tracking and understanding current research on reasoning abilities in large language models (LLMs).

• llm-as-classical-rl-implementer

  📘 Focus: Exploring how LLMs are used to implement classical reinforcement learning (RL) algorithms.

---

Thanks for stopping by! ⭐️