Research ArticleARTIFICIAL INTELLIGENCE A formal methods approach to interpretable reinforcement learning for robotic planning View ORCID ProfileXiao Li1,*, View ORCID ProfileZachary Serlin1, Guang Yang2 and Calin Belta1,21Department of Mechanical Engineering, Boston University, Boston, MA, USA.2Division of Systems Engineering, Boston University, Boston, MA, USA.↵*Corresponding author. Email: xli87{at}bu.edu See allHide authors and affiliations Science Robotics 18 Dec 2019:Vol. 4, Issue 37, eaay6276DOI: 10.1126/scirobotics.aay6276 Xiao Li 1Department of Mechanical Engineering, Boston University, Boston, MA, USA.Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Xiao Li For correspondence: xli87@bu.edu Zachary Serlin 1Department of Mechanical Engineering, Boston University, Boston, MA, USA.Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Zachary Serlin Guang Yang 2Division of Systems Engineering, Boston University, Boston, MA, USA.Find this author on Google Scholar Find this author on PubMed Search for this author on this site Calin Belta 1Department of Mechanical Engineering, Boston University, Boston, MA, USA.2Division of Systems Engineering, Boston University, Boston, MA, USA.Find this author on Google Scholar Find this author on PubMed Search for this author on this site Article Figures & Data Info & Metrics eLetters PDF Article Information vol. 4 no. 37 DOI: https://doi.org/10.1126/scirobotics.aay6276 Published By: Science Robotics History: Received July 5, 2019Accepted November 4, 2019 . Copyright & Usage: Copyright © 2019 The Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works http://www.sciencemag.org/about/science-licenses-journal-article-reuseThis is an article distributed under the terms of the Science Journals Default License. Author Information Xiao Li1,*, Zachary Serlin1, Guang Yang2 and Calin Belta1,21Department of Mechanical Engineering, Boston University, Boston, MA, USA.2Division of Systems Engineering, Boston University, Boston, MA, USA.↵*Corresponding author. Email: xli87{at}bu.edu Altmetric Article usage Article lifetimeLast 6 monthsThis monthArticle usage: December 2019 to March 2021 AbstractFullPdf Dec 201934579581487 Jan 20205987328202 Feb 2020619134127 Mar 202041910465 Apr 20202096641 May 20202516839 Jun 20202247627 Jul 20202085935 Aug 20201605140 Sep 20201657744 Oct 202027911150 Nov 202019411449 Dec 202017417180 Jan 202148215127 Feb 202134232102 Mar 202163616 View Full Text
A formal methods approach to interpretable reinforcement learning for robotic planning By Xiao Li, Zachary Serlin, Guang Yang, Calin Belta Science Robotics18 Dec 2019 A formal methods approach to reinforcement learning generates rewards from a formal language and guarantees safety. Supplementary Materials
A formal methods approach to interpretable reinforcement learning for robotic planning By Xiao Li, Zachary Serlin, Guang Yang, Calin Belta Science Robotics18 Dec 2019 A formal methods approach to reinforcement learning generates rewards from a formal language and guarantees safety. Supplementary Materials