About Me

Hi! I’m Chentian. I grew up in Norway and am pursuing an Informatics PhD at the University of Edinburgh, where I am supervised by Chris Lucas (Lucas Lab) and Frank Mollica.

During my PhD, I completed a Research Scientist Internship at DeepMind (Reinforcement Learning team) with Hado van Hasselt.

I am excited about topics in Computational Cognitive Science: my research aims to understand human learning strategies and build them into computational agents, with a focus on causal learning, generalization/meta-learning, and reinforcement learning. People are skilled at choosing actions to discover the causal relationships in their environment, including the abstract properties of these relationships that generalize to new situations. By studying their choices, I am interested in integrating human strategies into reinforcement learning agents.

Before starting my PhD, I worked in Data Science at Uptake (Chicago startup) and studied at Duke University, where I completed my Computer Science BSc with a Neuroscience minor and researched biomedical wearable devices in the Big Ideas Lab.

email | google scholar | github | linkedin

Education

PhD Informatics, 2023 (ongoing)
ILCC, University of Edinburgh
I am grateful to be funded by:

Principal’s Career Development Scholarship
Edinburgh Global Research Scholarship

BSc Computer Science, 2019
Minor Neuroscience
Duke University

Publications and Talks

Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration
Chentian Jiang, Nan Rosemary Ke, Hado van Hasselt
Accepted at Reincarnating RL Workshop at ICLR 2023
[ pdf ]

Actively learning to learn causal relationships
Chentian Jiang, Christopher G. Lucas
arXiv Preprint
[ preprint ]

Causal meta-learning by making informative interventions about the functional form
Chentian Jiang, Christopher G. Lucas
1-Page Abstract at the 16th Workshop for Women in Machine Learning at NeurIPS 2021 Selected as an outstanding abstract and featured as a [ contributed talk (click the “SlidesLive Video” button under “Chentian Jiang”) ]

Exploring Causal Overhypotheses in Active Learning
Chentian Jiang, Christopher G. Lucas
In Proceedings of the Annual Meeting of the Cognitive Science Society 2021
[ pdf ] [ poster ] [ preregistration ] [ 3min video summary ]

Pre-PhD

The Digital Biomarker Discovery Pipeline: An open source software platform for the development of digital biomarkers using mHealth and wearables data
Brinnae Bent, Ke Wang, Emilia Grzesiak, Chentian Jiang, Yuankai Qi, Yihang Jiang, Peter Cho, Kyle Zingler, Felix Ikponmwosa Ogbeide, Arthur Zhao, Ryan Runge, Ida Sim, Jessilyn Dunn
2020 Journal of Clinical and Translational Science
[ link ] [ pdf ]

Estimating Personal Resting Heart Rate from Wearable Biosensor Data
Chentian Jiang, Lida Faroqi, Latha Palaniappan, Jessilyn Dunn
2019 IEEE BHI
[ link ]