Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior

Tathagata Chakraborti; Anagha Kulkarni; Sarath Sreedharan; David E. Smith; Subbarao Kambhampati

Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior

Tathagata Chakraborti, Anagha Kulkarni, Sarath Sreedharan, David E. Smith, Subbarao Kambhampati

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for "explicable", "legible", "predictable" and "transparent" planning with overlapping, and sometimes conflicting, semantics all aimed at some notion of understanding what intentions the observer will ascribe to an agent by observing its behavior. This is also true for the recent works on "security" and "privacy" of plans which are also trying to answer the same question, but from the opposite point of view - i.e. when the agent is trying to hide instead of reveal its intentions. This paper attempts to provide a workable taxonomy of relevant concepts in this exciting and emerging field of inquiry.

Original language	English (US)
Title of host publication	Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019
Editors	J. Benton, Nir Lipovetzky, Eva Onaindia, David E. Smith, Siddharth Srivastava
Publisher	AAAI press
Pages	86-96
Number of pages	11
ISBN (Electronic)	9781577358077
State	Published - 2019
Event	29th International Conference on Automated Planning and Scheduling, ICAPS 2019 - Berkeley, United States Duration: Jul 11 2019 → Jul 15 2019

Publication series

Name	Proceedings International Conference on Automated Planning and Scheduling, ICAPS
ISSN (Print)	2334-0835
ISSN (Electronic)	2334-0843

Conference

Conference	29th International Conference on Automated Planning and Scheduling, ICAPS 2019
Country/Territory	United States
City	Berkeley
Period	7/11/19 → 7/15/19

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Information Systems and Management

Cite this

Chakraborti, T., Kulkarni, A., Sreedharan, S., Smith, D. E., & Kambhampati, S. (2019). Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior. In J. Benton, N. Lipovetzky, E. Onaindia, D. E. Smith, & S. Srivastava (Eds.), Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019 (pp. 86-96). (Proceedings International Conference on Automated Planning and Scheduling, ICAPS). AAAI press.

Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior. / Chakraborti, Tathagata; Kulkarni, Anagha; Sreedharan, Sarath et al.
Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019. ed. / J. Benton; Nir Lipovetzky; Eva Onaindia; David E. Smith; Siddharth Srivastava. AAAI press, 2019. p. 86-96 (Proceedings International Conference on Automated Planning and Scheduling, ICAPS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Chakraborti, T, Kulkarni, A, Sreedharan, S, Smith, DE & Kambhampati, S 2019, Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior. in J Benton, N Lipovetzky, E Onaindia, DE Smith & S Srivastava (eds), Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019. Proceedings International Conference on Automated Planning and Scheduling, ICAPS, AAAI press, pp. 86-96, 29th International Conference on Automated Planning and Scheduling, ICAPS 2019, Berkeley, United States, 7/11/19.

Chakraborti T, Kulkarni A, Sreedharan S, Smith DE, Kambhampati S. Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior. In Benton J, Lipovetzky N, Onaindia E, Smith DE, Srivastava S, editors, Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019. AAAI press. 2019. p. 86-96. (Proceedings International Conference on Automated Planning and Scheduling, ICAPS).

Chakraborti, Tathagata ; Kulkarni, Anagha ; Sreedharan, Sarath et al. / Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior. Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019. editor / J. Benton ; Nir Lipovetzky ; Eva Onaindia ; David E. Smith ; Siddharth Srivastava. AAAI press, 2019. pp. 86-96 (Proceedings International Conference on Automated Planning and Scheduling, ICAPS).

@inproceedings{2fe9bb48ecc64e5eb355ad7bf4ac9f40,

title = "Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior",

abstract = "There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for {"}explicable{"}, {"}legible{"}, {"}predictable{"} and {"}transparent{"} planning with overlapping, and sometimes conflicting, semantics all aimed at some notion of understanding what intentions the observer will ascribe to an agent by observing its behavior. This is also true for the recent works on {"}security{"} and {"}privacy{"} of plans which are also trying to answer the same question, but from the opposite point of view - i.e. when the agent is trying to hide instead of reveal its intentions. This paper attempts to provide a workable taxonomy of relevant concepts in this exciting and emerging field of inquiry.",

author = "Tathagata Chakraborti and Anagha Kulkarni and Sarath Sreedharan and Smith, {David E.} and Subbarao Kambhampati",

note = "Publisher Copyright: {\textcopyright} 2019, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 29th International Conference on Automated Planning and Scheduling, ICAPS 2019 ; Conference date: 11-07-2019 Through 15-07-2019",

year = "2019",

language = "English (US)",

series = "Proceedings International Conference on Automated Planning and Scheduling, ICAPS",

publisher = "AAAI press",

pages = "86--96",

editor = "J. Benton and Nir Lipovetzky and Eva Onaindia and Smith, {David E.} and Siddharth Srivastava",

booktitle = "Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019",

}

TY - GEN

T1 - Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior

AU - Chakraborti, Tathagata

AU - Kulkarni, Anagha

AU - Sreedharan, Sarath

AU - Smith, David E.

AU - Kambhampati, Subbarao

PY - 2019

Y1 - 2019

N2 - There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for "explicable", "legible", "predictable" and "transparent" planning with overlapping, and sometimes conflicting, semantics all aimed at some notion of understanding what intentions the observer will ascribe to an agent by observing its behavior. This is also true for the recent works on "security" and "privacy" of plans which are also trying to answer the same question, but from the opposite point of view - i.e. when the agent is trying to hide instead of reveal its intentions. This paper attempts to provide a workable taxonomy of relevant concepts in this exciting and emerging field of inquiry.

AB - There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for "explicable", "legible", "predictable" and "transparent" planning with overlapping, and sometimes conflicting, semantics all aimed at some notion of understanding what intentions the observer will ascribe to an agent by observing its behavior. This is also true for the recent works on "security" and "privacy" of plans which are also trying to answer the same question, but from the opposite point of view - i.e. when the agent is trying to hide instead of reveal its intentions. This paper attempts to provide a workable taxonomy of relevant concepts in this exciting and emerging field of inquiry.

UR - http://www.scopus.com/inward/record.url?scp=85074912600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074912600&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85074912600

T3 - Proceedings International Conference on Automated Planning and Scheduling, ICAPS

SP - 86

EP - 96

BT - Proceedings of the 29th International Conference on Automated Planning and Scheduling, ICAPS 2019

A2 - Benton, J.

A2 - Lipovetzky, Nir

A2 - Onaindia, Eva

A2 - Smith, David E.

A2 - Srivastava, Siddharth

PB - AAAI press

T2 - 29th International Conference on Automated Planning and Scheduling, ICAPS 2019

Y2 - 11 July 2019 through 15 July 2019

ER -

Explicability? legibility? predictability? transparency? privacy? security? The emerging landscape of interpretable agent behavior

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this