Jump to Content

Sai Zhang

Dr. Sai Zhang is a software engineer at Google in Kirkland, Washington, where he leads a team to build configuration management platform and product for Cloud customers. He is broadly interested in programming languages, software systems, software engineering, and security. He has a PhD from the University of Washington where he worked on a variety of research topics related to program analysis, programming systems, developer tools, and human computer interaction.
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Reward Shaping for User Satisfaction in a REINFORCE Recommender
    Can Xu
    Sriraj Badam
    Trevor Potter
    Daniel Li
    Hao Wan
    Elaine Le
    Chris Berg
    Eric Bencomo Dixon
    Preview abstract How might we design Reinforcement Learning (RL)-based recommenders that encourage aligning user trajectories with the underlying user satisfaction? Three research questions are key: (1) measuring user satisfaction, (2) combatting sparsity of satisfaction signals, and (3) adapting the training of the recommender agent to maximize satisfaction. For measurement, it has been found that surveys explicitly asking users to rate their experience with consumed items can provide valuable orthogonal information to the engagement/interaction data, acting as a proxy to the underlying user satisfaction. For sparsity, i.e, only being able to observe how satisfied users are with a tiny fraction of user-item interactions, imputation models can be useful in predicting satisfaction level for all items users have consumed. For learning satisfying recommender policies, we postulate that reward shaping in RL recommender agents is powerful for driving satisfying user experiences. Putting everything together, we propose to jointly learn a policy network and a satisfaction imputation network: The role of the imputation network is to learn which actions are satisfying to the user; while the policy network, built on top of REINFORCE, decides which items to recommend, with the reward utilizing the imputed satisfaction. We use both offline analysis and live experiments in an industrial large-scale recommendation platform to demonstrate the promise of our approach for satisfying user experiences. View details
    No Results Found