Viet Dung Nguyen
Papers
1
Total Citations
2
H-Index
1
About
Viet Dung Nguyen is a rising researcher at the forefront of artificial intelligence and robotics, specializing in active inference, world models, and reinforcement learning under partial observability. His most-cited work, "SR-AIF: Solving Sparse-Reward Robotic Tasks From Pixels with Active Inference and World Models" (2025), tackles one of the field's hardest challenges: enabling robots to learn from raw visual inputs with minimal feedback. By integrating active inference with learned world models, Nguyen's approach allows agents to efficiently explore and solve complex tasks in partially observable environments—a significant advance over traditional reinforcement learning methods that struggle with sparse rewards. Though early in his career, his work has already garnered attention, with 2 citations for this seminal paper. Nguyen's contributions bridge theoretical frameworks in neuroscience-inspired AI with practical robotic applications, offering a path toward more autonomous and adaptable systems. His research is particularly notable for addressing the gap between idealized Markov decision processes and real-world robotic scenarios, making his work essential reading for students and researchers interested in embodied intelligence, active inference, and sample-efficient learning.
Research Focus
Key Achievements
Top Papers
- 1