Felipe Trevizan

Felipe W. Trevizan

Email:
Phone:
+61 2 6218 3757
Office:
Data61 - S227
Building 108, North Road
Australian National University Campus
Canberra ACT 2601, Australia

I am a senior researcher in the Foundations and Methods of Machine Learning Team at Data61 (formerly known as NICTA) and an adjunct research fellow at the College of Engineering and Computer Science, Australian National University. My research interests are: planning under uncertainty, decision-theoretic planning, heuristic search, and reinforcement learning.

  • News and Highlights
    • ASNets: Learning generalized policies for SSPs using neural nets (AAAI'18).
    • h-pom, h-roc, and i2-dual won the best paper award at ICAPS'17!
    • New efficient approach to solve SSPs and C-SSPs with dead ends (UAI'17).
    • Solving SSPs and MDPs with PCTL* constraints (TABLEAUX'17).
    • h-pom and h-roc: the first heuristics able to handle probabilities and costs for SSPs and C-SSPs (ICAPS'17).
    • i-dual won the best paper award at ICAPS'16!
    • QTM won the best paper award from the AI committee of TRB'16! (demo).
    • i-dual: combining AI and OR to efficiently solve constrained SSPs (ICAPS'16).
  • Word cloud of my papers:
  • wordcloud
    large wordcloud