Felipe Trevizan

Felipe W. Trevizan

Email:
Office:
Building 108, North Road
Australian National University Campus
Canberra ACT 2601, Australia

I am an assistant professor in the Artificial Intelligence Group at the Australian National University. My research interests lie at the intersection of Artificial Intelligence, Operations Research and Machine Learning including automated planning and scheduling, planning under uncertainty, heuristic search, and reinforcement learning.

Recent Publications (full list here)

  • Action Schema Networks: Generalised Policies with Deep Learning. (2018) Toyer, S., Trevizan, F., Thiébaux, S. and Lexing, X. In Proc. of 32nd AAAI Conference on Artificial Intelligence. [pdf] [bib] [code]
  • Operator Counting Heuristics for Probabilistic Planning. (2018) Trevizan, F., Thiébaux, S. and Haslum, P. In Proc. of the 27th Int. Joint Conf. on AI (IJCAI). (Sister Conference Best Paper Track) [pdf] [bib]
  • Occupation Measure Heuristics for Probabilistic Planning. (2017) Trevizan, F., Thiébaux, S. and Haslum, P. In Proc. of 27th Int. Conf. on Automated Planning and Scheduling (ICAPS). (Best Paper Award) [pdf] [bib]
  • Efficient Solutions for Stochastic Shortest Path Problems with Dead Ends. (2017) Trevizan, F., Teichteil-Königsbuch, F. and Thiébaux, S. In Proc. of 33rd Int. Conf. on Uncertainty in Artificial Intelligence (UAI). [pdf] [bib]
  • 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 Kikuchi-Karlaftis best paper award at TRB'16! (demo).
    • i-dual: combining AI and OR to efficiently solve constrained SSPs (ICAPS'16).
  • Word cloud of my papers
  • wordcloud
    large wordcloud