Pragmatic-Pedagogic Value Alignment

Jaime F. Fisac, Monica A. Gates, Jessica B. Hamrick, Chang Liu, Dylan Hadfield-Menell, Malayandi Palaniappan, Dhruv Malik, S. Shankar Sastry, Thomas L. Griffiths, Anca D. Dragan

Research output: Chapter in Book/Report/Conference proceedingChapter

6 Scopus citations

Abstract

As intelligent systems gain autonomy and capability, it becomes vital to ensure that their objectives match those of their human users; this is known as the value-alignment problem. In robotics, value alignment is key to the design of collaborative robots that can integrate into human workflows, successfully inferring and adapting to their users’ objectives as they go. We argue that a meaningful solution to value alignment must combine multi-agent decision theory with rich mathematical models of human cognition, enabling robots to tap into people’s natural collaborative capabilities. We present a solution to the cooperative inverse reinforcement learning (CIRL) dynamic game based on well-established cognitive models of decision making and theory of mind. The solution captures a key reciprocity relation: the human will not plan her actions in isolation, but rather reason pedagogically about how the robot might learn from them; the robot, in turn, can anticipate this and interpret the human’s actions pragmatically. To our knowledge, this work constitutes the first formal analysis of value alignment grounded in empirically validated cognitive models.

Original languageEnglish (US)
Title of host publicationSpringer Proceedings in Advanced Robotics
PublisherSpringer Science and Business Media B.V.
Pages49-57
Number of pages9
DOIs
StatePublished - 2020
Externally publishedYes

Publication series

NameSpringer Proceedings in Advanced Robotics
Volume10
ISSN (Print)2511-1256
ISSN (Electronic)2511-1264

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Mechanical Engineering
  • Engineering (miscellaneous)
  • Artificial Intelligence
  • Computer Science Applications
  • Applied Mathematics

Keywords

  • Dynamic game theory
  • Human-robot interaction
  • Value alignment

Fingerprint

Dive into the research topics of 'Pragmatic-Pedagogic Value Alignment'. Together they form a unique fingerprint.

Cite this