Publications and Preprints

2026

  1. NeurIPS
    Training Generalizable Collaborative Agents via Strategic Risk Aversion
    Chengrui Qu, Yizhou Zhang, Nicola Lanzetti, and Eric Mazumdar
    In Proceedings of the 40th Conference on Neural Information Processing Systems (NeurIPS), Oral (0.4%) , 2026
    arXiv
  2. NeurIPS
    Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy Remedies
    Yizhou Zhang*, Yashaswini Murthy*, Laixi Shi, and Adam Wierman
    In Proceedings of the 40th Conference on Neural Information Processing Systems (NeurIPS), 2026
  3. ICML
    Provably Convergent Actor-Critic for MARL through Risk-aversion
    Yizhou Zhang and Eric Mazumdar
    In Proceedings of the 43rd International Conference on Machine Learning (ICML), Spotlight (2.2%) , 2026
    arXiv

2025

  1. CDC
    Convergent Q-Learning for Infinite-Horizon General-Sum Markov Games through Behavioral Economics
    Yizhou Zhang and Eric Mazumdar
    In Proceedings of the 64th IEEE Conference on Decision and Control (CDC), 2025
    DOI HTML
  2. arXiv
    KL-regularization Itself is Differentially Private in Bandits and RLHF
    Yizhou Zhang, Kishan Panaganti, Laixi Shi, Juba Ziani, and Adam Wierman
    In submission , 2025
    arXiv
  3. ICML
    Learning to Steer Learners in Games
    Yizhou Zhang, Yian Ma, and Eric Mazumdar
    In Proceedings of the 42nd International Conference on Machine Learning (ICML), 2025
    arXiv

2023

  1. POMACS
    Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning
    Yizhou Zhang*, Guannan Qu*, Pan Xu*, Yiheng Lin, Zaiwei Chen, and Adam Wierman
    Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2023
    DOI