Independent researcher & software engineer

Learning systems.
Real-world questions.

I'm Huy, a researcher and engineer in Hanoi, Vietnam. My work explores how learning agents cooperate, adapt to context, and make better decisions in complex environments.

Explore my research Get in touch

Multi-agent RLIntelligent transportationApplied AI

A question from my research

What changes when an
ambulance needs to pass?

Intersection agents coordinate to manage regular traffic.

Conceptual illustration, not a simulation or experimental result.

Selected research

Cooperation, context,
and better traffic control.

My research connects multi-agent reinforcement learning with context-aware decisions in urban transportation.

2026Journal article

International Journal of Intelligent Transportation Systems Research

A Dual-Mode Multi-Agent Reinforcement Learning Method for Context-Aware Traffic Control Optimization

Nhat Quang Doan, Nhat Huy Ly, Anh Tuan Giang, Hoang Ha Nguyen

Dual-policy traffic signal control that responds to ordinary traffic and emergency vehicles. I contributed to methodology, development, and simulation.

Read paper ↗Research code ↗

Research contribution

The DM-MADDPG project builds on my earlier MOP-MADDPG work, using separate reward and policy structures for context-dependent traffic control. The journal's contribution statement credits me with research and methodology, simulation, and development.

2025Conference paper

17th International Conference on Knowledge and Systems Engineering (KSE) · IEEE

Enhancing Urban Traffic Control with Priority-Aware Multi-Objective Reinforcement Learning

N. H. Ly, N. Q. Doan, A. T. Giang, H. T. Le, H. H. Nguyen, H. T. Tran

My MOP-MADDPG research project and bachelor's thesis investigated multi-objective traffic control using PyTorch, SUMO, and custom reinforcement learning environments.

View publication ↗Research code ↗

About

From research
to working systems.

I combine experimental research with hands-on software engineering: turning a question into an algorithm, testing it in simulation, and building the systems around it.

I currently conduct research independently. USTH is my alma mater and a past research setting, not a current institutional appointment.

ORCID: 0009-0002-7829-139X ↗

March 2026 – present

Technical Lead / Fullstack

BPSS.Cloud · Remote

System architecture and technical decisions, including real-time translation, noise filtering, and contextual awareness.

April – July 2025

Research Intern

USTH ICT Lab · Hanoi

Faculty-supervised work on multi-agent reinforcement learning, traffic signal optimization, and SUMO experiments using Hanoi road networks.

2022 – 2025

BSc, Information & Communication Technology

University of Science and Technology of Hanoi

English-taught program, with coursework in deep learning, algorithms, software architecture, and reinforcement learning.

Selected engineering work

ParentLink

A real-time child-safety tracker with a Golang backend and WebRTC video and audio. Team leader and full-stack developer.

Golang / WebRTCView code ↗

Twitter (X) Clone

A social platform project with real-time chat and notifications, built with Node.js, PostgreSQL, and WebSockets. Team leader and full-stack developer.

Node.js / PostgreSQLView code ↗

Contact

Let's talk research.

For questions about my work, research discussions, or engineering collaboration, email me.

lynhathuy38@gmail.com