About Me

I am currently a research scientist at Meta, where I am working on recommendation systems.

Previously, I was a PhD student at Princeton University working on theoretical analyses of meta-learning, where I was advised by Jason D. Lee. Before then, I studied EE/CS at UC Berkeley, where I worked on model-based reinforcement learning together with Sergey Levine, Roberto Calandra, and Rowan McAllister.

Publications

• Provable Hierarchy-Based Meta-Reinforcement Learning
  Kurtland Chua, Qi Lei, Jason D. Lee.
  AISTATS 2023.

• How Fine-Tuning Allows for Effective Meta-Learning.
  Kurtland Chua, Qi Lei, Jason D. Lee.
  NeurIPS 2021.

• On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning.
  Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra.
  AISTATS 2021.

• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models.
  website | code
  Kurtland Chua, Roberto Calandra, Rowan McAllister, Sergey Levine.
  NeurIPS 2018 (Spotlight presentation, ~4% of submitted papers).

Talks

• “Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models.” Bay Area Machine Learning Symposium (Baylearn). October 2018.
  video

Teaching

• COS 435: Introduction to Reinforcement Learning, Princeton
  Assistant in Instruction
  Spring 2024

• COS 240: Reasoning about Computation, Princeton
  Assistant in Instruction
  Fall 2023

• EECS 126: Probability and Random Processes, UC Berkeley
  Undergraduate Student Instructor (uGSI)
  Spring 2019 | Fall 2018

Honors and Awards

• National Science Foundation Graduate Research Fellowship (2019).
• Gordon Y.S. Wu Fellowship in Engineering (2019).
• EECS Major Citation (2019).
• NVIDIA Pioneer Award (2018). Awarded for Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models at NeurIPS 2018.
• Phi Beta Kappa Honors Society (2018). Inducted as a junior.