Việt Bắc Nguyễn

I am a motivated AI student focused on Reinforcement Learning and Large Language Models, with practical research in fine-tuning agents via RLHF/RLAIF for context-aware decision-making.

I have experience applying game theory and cooperative reinforcement learning to improve multi-agent collaboration, and I completed a thesis on benefit allocation using Shapley value to accelerate learning. I also interned as an AI Engineer working on entity linking, fine-tuning BERT and Transformer-based models.

Technically proficient in Python, C++, Java, PyTorch, TensorFlow and Transformers, I build applied systems such as PDF-to-text extraction, sentiment classifiers, image recognition pipelines, recommendation engines, and an AI-enhanced text editor (SmartNoteAI).