Jubayer Ibn Hamid

I am a PhD student at Stanford University. Previously, I studied mathematical physics as an undergraduate at Stanford University.

I work in artificial intelligence with a focus on sequential decision making and reinforcement learning. I am also interested in pure mathematics, especially abstract algebra and neighboring fields.

My research is advised by Chelsea Finn and Dorsa Sadigh. I am currently in my first year of PhD and am affiliated with Stanford Artificial Intelligence Laboratory (SAIL).

Selected Publications

• Polychromic Objectives for Reinforcement Learning. Jubayer Ibn Hamid*, Ifdita Hasan Orney*, Ellen Xu, Chelsea Finn, Dorsa Sadigh. Preprint.

• Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling. Yuejiang Liu*, Jubayer Ibn Hamid*, Annie Xie, Yoonho Lee, Max Du, Chelsea Finn. International Conference on Learning Representations (ICLR), 2025. (Website)

(*) denotes co-first authorship

Full list of publications can be found here: Publications.

Notes

Introductory notes on various topics I have found to be fascinating and/or useful in my own research.

• Category Theory and Algebraic Geometry. Notes on introductory category theory and foundational constructions in algebraic geometry (work in progress).

• Abstract Algebra. Notes on abstract algebra (work in progress).

• Whitney's Embedding Theorem and Immersion Theorem. Weak versions of Whitney's Embedding and Immersion theorem, which are often sufficient.

• Policy Gradient Methods. Building blocks of policy gradient methods in online reinforcement learning.

• Trust Region Optimization Methods. Introduction to trust region methods for optimization.

Teaching

CS 224R - Deep Reinforcement Learning. Head CA. Spring, 2025.

CS 229 - Machine Learning. CA. Winter, 2025.