Objective learning from human demonstrations

Jonathan Feng-Shun Lin, Pamela Carreno-Medrano, Mahsa Parsapour, Maram Sakr, Dana Kulić

Research output: Contribution to journalReview ArticleResearchpeer-review

7 Citations (Scopus)

Abstract

Researchers in biomechanics, neuroscience, human–machine interaction and other fields are interested in inferring human intentions and objectives from observed actions. The problem of inferring objectives from observations has received extensive theoretical and methodological development from both the controls and machine learning communities. In this paper, we provide an integrating view of objective learning from human demonstration data. We differentiate algorithms based on the assumptions made about the objective function structure, how the similarity between the inferred objectives and the observed demonstrations is assessed, the assumptions made about the agent and environment model, and the properties of the observed human demonstrations. We review the application domains and validation approaches of existing works and identify the key open challenges and limitations. The paper concludes with an identification of promising directions for future work.

Original languageEnglish
Pages (from-to)111-129
Number of pages19
JournalAnnual Reviews in Control
Volume51
DOIs
Publication statusPublished - 2021

Keywords

  • Inverse optimal control
  • Inverse reinforcement learning
  • Reward learning

Cite this