Dillon Z. Chen

prof_pic.png

I am a PhD student at the University of Toronto. I build AI systems that solve long-horizon planning problems over complex, dynamic environments.

My research interests include learning and planning with world models.

My recent work focuses on generalised planning – the task of learning programs that generalise across planning problems. I designed systems over symbolic world models that few-shot learn policies from simple demonstrations with 100x gains over the state of the art.

Click here to play the dog gacha.

Selected Publications

A full list of my publications is available on Google Scholar.
  1. Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning
    Dillon Z. Chen, Till Hofmann, Toryn Q. Klassen, and Sheila A. McIlraith
    arXiv preprint, 2026
    arXiv Code Website
  2. moose.png
    Satisficing and Optimal Generalised Planning via Goal Regression
    Dillon Z. Chen, Till Hofmann, Toryn Q. Klassen, and Sheila A. McIlraith
    AAAI, 2026. Oral
    arXiv Code
  3. lmplan.png
    Language Models For Generalised PDDL Planning: Synthesising Sound and Programmatic Policies
    Dillon Z. Chen, Johannes Zenn, Tristan Cinquin, and Sheila A. McIlraith
    EWRL, 2025
    arXiv Code
  4. goose.png
    Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning
    Dillon Z. Chen, Felipe Trevizan, and Sylvie Thiébaux
    ICAPS, 2024
    arXiv Code Website
  5. mossp.png
    Heuristic Search for Multi-Objective Probabilistic Planning
    Dillon Z. Chen, Felipe Trevizan, and Sylvie Thiébaux
    AAAI, 2023. Oral
    arXiv
  6. fondhtn.png
    Flexible FOND HTN Planning: A Complexity Analysis
    Dillon Z. Chen and Pascal Bercher
    ICAPS, 2022. Best Undergraduate Student Paper Award
    PDF