Khang Nguyen

MS student in Mathematical Data Science at USC. Reinforcement learning theory with William Chang's group (BruinML, UCLA).

About

I'm a master's student in Mathematical Data Science at USC, finishing in December 2026, and I do reinforcement learning theory with William Chang's group at UCLA. Most of my work is on bandits and online learning: best-arm identification, adversarial and corrupted MDPs, continuous action spaces, and how fast entropy regularization approximates equilibria in continuous games. Alongside the theory I build things, most recently the LLM agent behind Coursistant's classroom assistant.

Research interests

Bandits and online learning, best-arm identification, adversarial and corrupted MDPs, continuous action spaces, equilibria in continuous games.

Publications and preprints

* equal contribution, alphabetical order

Published or accepted

  • Tight rates of approximation of mixed Nash equilibria by entropy regularization in continuous games K. Nguyen, V. Iverson, S. Wijetunga, W. Chang, G. Wang UAI 2026 First author. Proved most of the results, wrote most of the paper and the rebuttal, ran the numerics. proceedingsPDF
  • Gap-Independent Regret for Multi-Agent Combinatorial Semi-Bandits B. Chen, K. Nguyen, J. Liu, X. Li, Y. Luo, W. Chang EWRL 2026 Tightened most of the proofs; wrote the experiment code. code
  • A pathological property of nonlocal discrete operators W. Chang*, C. S. Goodrich*, V. Iverson*, K. Nguyen* Proc. AMS Ser. B Equal contribution (alphabetical). Independently proved the central algebraic identity. DOI
  • Minimum-Energy Optimal Gaze Control for K-Eye Systems with Three-Axis Rotation K. Nguyen, L. Jones, W. Chang IFAC CPHS 2026 First author.

Under review

  • Hybrid Offline-Online Follower Manipulation in General-Sum Stackelberg Games M. S. Lin, K. Nguyen, B. Chen, J. Q. Loi, V. Bansal, W. Chang NeurIPS 2026 (under review)
  • Learning Adversarial Continuous MDPs with Bandit Feedback and Unknown Transitions A. Kulkarni, K. Nguyen, R. Parada, K. Guo, W. Chang, Y. Dai NeurIPS 2026 (under review)
  • Policy Optimization for Corrupted Markov Decision Processes K. Nguyen, K. Guo, W. Chang AAAI 2027 (under review) First author.
  • Best Arm Identification in Lipschitz Bandits: Uniform and Adaptive Strategies K. Nguyen, L. Xu, L. Jiang, W. Chang AAAI 2027 (under review) First author.
  • Pure Exploration for Curriculum Bandits J. Q. Loi, B. Chen, K. Nguyen, W. Chang, N. Weinberger AAAI 2027 (under review)
  • ZoomQ: Adaptive Action Discretization for Continuous-Action RL T. Iyadomi, L. Xu, K. Nguyen, R. Parada, W. Chang, S. Yogamani AAAI 2027 (under review)

Selected projects

Teaching

Teaching assistant, DSCI 560 Data Science Professional Practicum (algorithmic trading), USC, Spring 2026.