Safe Reinforcement Learning Using Black-Box Reachability Analysis

Mahmoud Selim, Amr Alanwar, Shreyas Kousik, Grace Gao, Marco Pavone, Karl H. Johansson

Research output: Contribution to journalArticlepeer-review

24 Citations (Scopus)
Original languageEnglish
Pages (from-to)10665-10672
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume7
Issue number4
DOIs
Publication statusPublished - Oct 1 2022
Externally publishedYes

ASJC Scopus Subject Areas

  • Control and Systems Engineering
  • Biomedical Engineering
  • Human-Computer Interaction
  • Mechanical Engineering
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Control and Optimization
  • Artificial Intelligence

Keywords

  • Reinforcement learning
  • robot safety
  • task and motion planning

Fingerprint

Dive into the research topics of 'Safe Reinforcement Learning Using Black-Box Reachability Analysis'. Together they form a unique fingerprint.

Cite this

Selim, M., Alanwar, A., Kousik, S., Gao, G., Pavone, M., & Johansson, K. H. (2022). Safe Reinforcement Learning Using Black-Box Reachability Analysis. IEEE Robotics and Automation Letters, 7(4), 10665-10672. https://doi.org/10.1109/LRA.2022.3192205