About
I am a Bachelor of Science student at the University of Sydney, majoring in Mathematics and Computer Science.
I am primarily interested in Continual Reinforcement Learning. My goal is to understand how agents can continually learn and adapt as their environments change, and how to evaluate that progress reliably.
News: My paper was accepted to the NeurIPS 2026 Continual World Model Workshop. Read more →
Research Interests
- Continual Reinforcement LearningHow long-lived agents learn continuously from observation, action, and reward in changing environments, developing representations and world models for prediction, planning, and control without domain-specific prior knowledge.
- Fundamental Principles of IntelligenceHow intelligence can be understood through general principles of learning, inference, and decision-making, drawing on active inference and algorithmic information theory.
- Mind and ConsciousnessHow cognition and subjective experience arise through the interaction of mind, body, and environment, explored through embodied cognition and computational phenomenology.
Papers
World Drift or Question Drift? Question Identity as a Precondition for Continual World Model Evaluation
Shanglong Hu
Continual World Model Workshop, NeurIPS 2026 · Accepted · Non-archival
Experience
July 2026,
Shanghai
Predictive State Representations for Continual Reinforcement Learning: An Exploratory Study
Team Project
Thoughtfulness Award ↗