Dr. Felipe Trevizan is currently an Assistant Professor in the Research School of Computer Science at the Australian National University (ANU). Previously, Felipe was a Senior Research Scientist at NICTA (now Data61/CSIRO). Felipe earned his Ph.D. in Machine Learning (2013) from Carnegie Mellon University (CMU) under the supervision of Prof. Manuela Veloso. In his thesis, Felipe introduced short-sighted planning, a novel approach to effectively plan under uncertainty. As part of his Ph.D. program, Felipe received a M.Sc. degree (2010) where he showed how to use machine learning techniques to classify the opponent's strategy in the RoboCup small size league.

Before joining CMU, Felipe received his first M.Sc. degree (2006) and his Bachelor of Computer Science degree (2004) from Instituto de Matemática e Estatística at Universidade de São Paulo under the supervision of Prof. Leliane Nunes de Barros. In this M.Sc. thesis, Felipe introduced a new model for planning under uncertainty in which actions can be either probabilistic, non-deterministic or anything in between. For his research project for undergraduates, Felipe programmed Lego Mindstorm robots using deterministic planners and automatic theorem provers.

Felipe's research interests lie at the intersection of Artificial Intelligence, Operations Research and Machine Learning including automated planning and scheduling, reasoning under uncertainty, heuristic search, and reinforcement learning.

Along with colleagues and students, Felipe is the co-recipient of the 2016 Kikuchi-Karlaftis Best Paper Award of the Transport Research Board and the Best Paper Award in at the International Conference on Automated Planning and Scheduling (ICAPS) in 2016 and 2017.

For more details, see Felipe's CV, Google Scholar profile and DBLP entry.

  • News and Highlights
    • STRIPS-HGN: First algorithm capable of learning domain-independent heuristics from scratch (ICAPS'20).
    • New insights and results for ASNets on JAIR
    • Guiding search using generalized policies from ASNets (SoCS'19)
    • PLTL-dual: First heuristic search algorithm for SSPs and MDPs with Probabilistic LTL constraints (KR'18).
    • 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).
    • 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).
  • Word cloud of my papers
  • wordcloud
    large wordcloud