Xin Zhang

I am a Ph.D. candidate in the Department of Data Science at Worcester Polytechnic Institute. My research interests include imitation-learning, meta-learning, human behavior analysis and spatial-temporal data mining. My works have appeared in NeurIPS, ICDM and TBD. I am a member of DSRG, working with Prof. Yanhua Li.


Research Interests

  • Imitation Learning

  • Meta-Learning

  • Human Behavior Analysis
  • Spatial-temporal Data Mining

  Education


>>>News:



Experience

  • Program Committee, AAAI 2022: The Thirty-Sixth AAAI Conference on Artificial Intelligence.
  • Research Intern, Laboratory of Prof. Yanhua Li, Worcester Polytechnic Institute.
    Aug 2018 - Present.
    Supervisor: Yanhua Li.
    Responsibilities include:
    • Proposed f-GAIL, a new generative adversarial imitation learning (GAIL) model, that automatically learns a discrepancy measure from the f-divergence family as well as a policy capable of producing expert-like behaviors.
    • Developed a TrajGAIL framework which captures the long-term decision dependency by modeling the human decision processes as variable length Markov decision processes (VLMDPs), and designs a deep-neural-network-based framework to inversely learn the decision-making strategy from the human agent’s historical dataset.
    • Designed a cGAIL model, as a unifying collective inverse reinforcement learning framework that learns taxi driver’s decision-making preferences and policies by transferring knowledge across taxi driver agents and across locations.




Contact