Dr. Felipe Trevizan is currently an Senior Lecturer in the School of Computing (formerly known as Research School of Computer Science) at the Australian National University (ANU). Previously, Felipe was a Senior Research Scientist at NICTA and 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 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
    • First heuristic search algorithms for Multi-Objective Stochastic Planning (AAAI'23).
    • New admissible heuristics for Multi-Objective Deterministic Planning (ICAPS'22).
    • New heuristics for SSPs with PLTL constraints! This time based on progression (AAAI'21).
    • I gave an Early Career Researcher Spotlight talk at the IJCAI-20.
    • STRIPS-HGN: First algorithm capable of learning domain-independent heuristics from scratch (ICAPS'20).
    • New insights and results for ASNets on JAIR.
    • 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!
    • i-dual won the best paper award at ICAPS'16!
  • Word cloud of my papers
  • wordcloud
    large wordcloud