Explaining BDI Agent Behaviour Through Dialogue

Louise A.  Dennis; Nir Oren

doi:10.1007/s10458-022-09556-8

Explaining BDI Agent Behaviour Through Dialogue

Louise A. Dennis, Nir Oren^* (Corresponding Author)

^*Corresponding author for this work

University of Manchester

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

5 Downloads (Pure)

Abstract

BDI agents act in response to external inputs and their internal plan library. Understanding the root cause of BDI agent action is often difficult, and in this paper we present a dialogue based approach for explaining the behaviour of a BDI agent. We consider two dialogue participants who may have different views regarding the beliefs, plans and external events which drove agent action (encoded via traces). These participants make utterances which incrementally reveal their traces to each other, allowing them to identify divergences in the traces, or to conclude that their traces agree. In practice, we envision a human taking on the role of a dialogue participant, with the BDI agent itself acting as the other participant. The dialogue then facilitates explanation, understanding and debugging of BDI agent behaviour. After presenting our formalism and its properties, we describe our implementation of the system and provide an example of its use in a simple scenario.

Original language	English
Article number	29
Number of pages	27
Journal	Autonomous Agents and Multi-Agent Systems
Volume	36
Early online date	6 May 2022
DOIs	https://doi.org/10.1007/s10458-022-09556-8
Publication status	Published - 6 May 2022

Bibliographical note

This work arose out of conversations at a Lorentz Workshop on the Dynamics of Multi-Agent Systems (2018). Thanks are due Koen Hindriks and Vincent Koeman for their input. The work was supported by the UKRI/EPSRC RAIN [EP/R026084], SSPEDI [EP/P011829/1 ] and FAIR-SPACE [EP/R026092] Robotics and AI Hubs and the Trustworthy Autonomous Systems Verifiability Node [EP/V026801/1]. Both authors contributed equally to the work, and author names are listed in alphabetical order.

Keywords

BDI
Explanation
Dialogues

Access to Document

10.1007/s10458-022-09556-8Licence: CC BY

Dennis_etal_AAMS_Explaining_BDI_Agent_VoR
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Final published version, 1.33 MBLicence: CC BY

Cite this

@article{c9af8ab197a9437bae119c5576fc30c8,

title = "Explaining BDI Agent Behaviour Through Dialogue",

abstract = "BDI agents act in response to external inputs and their internal plan library. Understanding the root cause of BDI agent action is often difficult, and in this paper we present a dialogue based approach for explaining the behaviour of a BDI agent. We consider two dialogue participants who may have different views regarding the beliefs, plans and external events which drove agent action (encoded via traces). These participants make utterances which incrementally reveal their traces to each other, allowing them to identify divergences in the traces, or to conclude that their traces agree. In practice, we envision a human taking on the role of a dialogue participant, with the BDI agent itself acting as the other participant. The dialogue then facilitates explanation, understanding and debugging of BDI agent behaviour. After presenting our formalism and its properties, we describe our implementation of the system and provide an example of its use in a simple scenario.",

keywords = "BDI, Explanation, Dialogues",

author = "Dennis, {Louise A.} and Nir Oren",

note = "This work arose out of conversations at a Lorentz Workshop on the Dynamics of Multi-Agent Systems (2018). Thanks are due Koen Hindriks and Vincent Koeman for their input. The work was supported by the UKRI/EPSRC RAIN [EP/R026084], SSPEDI [EP/P011829/1 ] and FAIR-SPACE [EP/R026092] Robotics and AI Hubs and the Trustworthy Autonomous Systems Verifiability Node [EP/V026801/1]. Both authors contributed equally to the work, and author names are listed in alphabetical order.",

year = "2022",

month = may,

day = "6",

doi = "10.1007/s10458-022-09556-8",

language = "English",

volume = "36",

journal = "Autonomous Agents and Multi-Agent Systems",

issn = "1387-2532",

publisher = "Springer Netherlands",

}

TY - JOUR

T1 - Explaining BDI Agent Behaviour Through Dialogue

AU - Dennis, Louise A.

AU - Oren, Nir

N1 - This work arose out of conversations at a Lorentz Workshop on the Dynamics of Multi-Agent Systems (2018). Thanks are due Koen Hindriks and Vincent Koeman for their input. The work was supported by the UKRI/EPSRC RAIN [EP/R026084], SSPEDI [EP/P011829/1 ] and FAIR-SPACE [EP/R026092] Robotics and AI Hubs and the Trustworthy Autonomous Systems Verifiability Node [EP/V026801/1]. Both authors contributed equally to the work, and author names are listed in alphabetical order.

PY - 2022/5/6

Y1 - 2022/5/6

N2 - BDI agents act in response to external inputs and their internal plan library. Understanding the root cause of BDI agent action is often difficult, and in this paper we present a dialogue based approach for explaining the behaviour of a BDI agent. We consider two dialogue participants who may have different views regarding the beliefs, plans and external events which drove agent action (encoded via traces). These participants make utterances which incrementally reveal their traces to each other, allowing them to identify divergences in the traces, or to conclude that their traces agree. In practice, we envision a human taking on the role of a dialogue participant, with the BDI agent itself acting as the other participant. The dialogue then facilitates explanation, understanding and debugging of BDI agent behaviour. After presenting our formalism and its properties, we describe our implementation of the system and provide an example of its use in a simple scenario.

AB - BDI agents act in response to external inputs and their internal plan library. Understanding the root cause of BDI agent action is often difficult, and in this paper we present a dialogue based approach for explaining the behaviour of a BDI agent. We consider two dialogue participants who may have different views regarding the beliefs, plans and external events which drove agent action (encoded via traces). These participants make utterances which incrementally reveal their traces to each other, allowing them to identify divergences in the traces, or to conclude that their traces agree. In practice, we envision a human taking on the role of a dialogue participant, with the BDI agent itself acting as the other participant. The dialogue then facilitates explanation, understanding and debugging of BDI agent behaviour. After presenting our formalism and its properties, we describe our implementation of the system and provide an example of its use in a simple scenario.

KW - BDI

KW - Explanation

KW - Dialogues

U2 - 10.1007/s10458-022-09556-8

DO - 10.1007/s10458-022-09556-8

M3 - Article

SN - 1387-2532

VL - 36

JO - Autonomous Agents and Multi-Agent Systems

JF - Autonomous Agents and Multi-Agent Systems

M1 - 29

ER -