I am a second-year Ph.D. student in Computer Science at National University of Singapore advised by Prof. Wee Sun Lee with a focus on reinforcement learning.
I received my Bachelor's degree in Statistics from Northwestern Polytechnical University, where I studied mathematics and statistics.
Research
I am broadly interested in reinforcement learning and decision-making. My current research focuses on active exploration, structured memory, multi-step world models, and hierarchical RL. The ultimate goal is to realize autonomous AI systems for a wide spectrum of applications that benefit the society.
The core research problems that I am actively working on and will continue to answer are
- Sample Efficiency How to acquire skills and adapt to novel situations with minimal data is a long-standing challenge in the field.
- World Models Predictive models with a universal state representation enable fine-grained planning and reasoning.
- Intrinsic Motivation Without hand-crafted rewards, how could an agent maintain its well-being and possibly refine its policy?
- Hierarchy Whatever level of abstraction occurs, hierarchy persists temporally and spatially in both decision-making and vision.
- Uncertainty Understanding the world by reducing epistemic uncertainty, and influencing it by maximizing reward in the face of aleatoric uncertainty.
Highlighted Works
- Discerning Temporal Difference Learning
- Jianfei Ma
AAAI, 2024
Paper - Generative Intrinsic Optimization: Intrinsic Control with Model Learning
- Jianfei Ma
NeurIPS Workshop IMOL, 2023
Paper - The Point to Which Soft Actor-Critic Converges
- Jianfei Ma
ICLR Tiny Papers, 2023
Paper - Distillation Policy Optimization
- Jianfei Ma
Preprint, 2023
Paper, Code - Entropy Augmented Reinforcement Learning
- Jianfei Ma
Preprint, 2022
Paper
