Towards learning from stories: An approach to interactive machine learning

Brent Harrison; Mark O. Riedl

Towards learning from stories: An approach to interactive machine learning

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

4 Scopus citations

Abstract

In this work, we introduce a technique that uses stories to train virtual agents to exhibit believable behavior. This technique uses a compact representation of a story to define the space of acceptable behaviors and then uses this space to assign rewards to certain world states. We show the effectiveness of our technique with a case study in a modified gridworld environment called Pharmacy World. The results show that a reinforcement learning agent using Q-learning was able to learn a policy that results in believable behavior.

Original language	English
Title of host publication	WS-16-01
Subtitle of host publication	Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence
Pages	746-750
Number of pages	5
ISBN (Electronic)	9781577357599
State	Published - 2016
Event	30th AAAI Conference on Artificial Intelligence, AAAI 2016 - Phoenix, United States Duration: Feb 12 2016 → Feb 17 2016

Publication series

Name	AAAI Workshop - Technical Report
Volume	WS-16-01 - WS-16-15

Conference

Conference	30th AAAI Conference on Artificial Intelligence, AAAI 2016
Country/Territory	United States
City	Phoenix
Period	2/12/16 → 2/17/16

Bibliographical note

Publisher Copyright:
Copyright © 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

ASJC Scopus subject areas

General Engineering

Cite this

Harrison, B., & Riedl, M. O. (2016). Towards learning from stories: An approach to interactive machine learning. In WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence (pp. 746-750). (AAAI Workshop - Technical Report; Vol. WS-16-01 - WS-16-15).

Harrison, Brent ; Riedl, Mark O. / Towards learning from stories : An approach to interactive machine learning. WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence. 2016. pp. 746-750 (AAAI Workshop - Technical Report).

@inproceedings{c3a4e05219da45c9bdc9f2cc7be2ea56,

title = "Towards learning from stories: An approach to interactive machine learning",

abstract = "In this work, we introduce a technique that uses stories to train virtual agents to exhibit believable behavior. This technique uses a compact representation of a story to define the space of acceptable behaviors and then uses this space to assign rewards to certain world states. We show the effectiveness of our technique with a case study in a modified gridworld environment called Pharmacy World. The results show that a reinforcement learning agent using Q-learning was able to learn a policy that results in believable behavior.",

author = "Brent Harrison and Riedl, {Mark O.}",

note = "Publisher Copyright: Copyright {\textcopyright} 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 30th AAAI Conference on Artificial Intelligence, AAAI 2016 ; Conference date: 12-02-2016 Through 17-02-2016",

year = "2016",

language = "English",

series = "AAAI Workshop - Technical Report",

pages = "746--750",

booktitle = "WS-16-01",

}

Harrison, B & Riedl, MO 2016, Towards learning from stories: An approach to interactive machine learning. in WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence. AAAI Workshop - Technical Report, vol. WS-16-01 - WS-16-15, pp. 746-750, 30th AAAI Conference on Artificial Intelligence, AAAI 2016, Phoenix, United States, 2/12/16.

Towards learning from stories: An approach to interactive machine learning. / Harrison, Brent; Riedl, Mark O.
WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence. 2016. p. 746-750 (AAAI Workshop - Technical Report; Vol. WS-16-01 - WS-16-15).

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

TY - GEN

T1 - Towards learning from stories

T2 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016

AU - Harrison, Brent

AU - Riedl, Mark O.

PY - 2016

Y1 - 2016

N2 - In this work, we introduce a technique that uses stories to train virtual agents to exhibit believable behavior. This technique uses a compact representation of a story to define the space of acceptable behaviors and then uses this space to assign rewards to certain world states. We show the effectiveness of our technique with a case study in a modified gridworld environment called Pharmacy World. The results show that a reinforcement learning agent using Q-learning was able to learn a policy that results in believable behavior.

AB - In this work, we introduce a technique that uses stories to train virtual agents to exhibit believable behavior. This technique uses a compact representation of a story to define the space of acceptable behaviors and then uses this space to assign rewards to certain world states. We show the effectiveness of our technique with a case study in a modified gridworld environment called Pharmacy World. The results show that a reinforcement learning agent using Q-learning was able to learn a policy that results in believable behavior.

UR - http://www.scopus.com/inward/record.url?scp=85022029517&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022029517&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85022029517

T3 - AAAI Workshop - Technical Report

SP - 746

EP - 750

BT - WS-16-01

Y2 - 12 February 2016 through 17 February 2016

ER -

Harrison B, Riedl MO. Towards learning from stories: An approach to interactive machine learning. In WS-16-01: Artificial Intelligence Applied to Assistive Technologies and Smart Environments; WS-16-02: AI, Ethics, and Society; WS-16-03: Artificial Intelligence for Cyber Security; WS-16-04: Artificial Intelligence for Smart Grids and Smart Buildings; WS-16-05: Beyond NP; WS-16-06: Computer Poker and Imperfect Information Games; WS-16-07: Declarative Learning Based Programming; WS-16-08: Expanding the Boundaries of Health Informatics Using AI; WS-16-09: Incentives and Trust in Electronic Communities; WS-16-10: Knowledge Extraction from Text; WS-16-11: Multiagent Interaction without Prior Coordination; WS-16-12: Planning for Hybrid Systems; WS-16-13: Scholarly Big Data: AI Perspectives, Challenges, and Ideas; WS-16-14: Symbiotic Cognitive Systems; WS-16-15: World Wide Web and Population Health Intelligence. 2016. p. 746-750. (AAAI Workshop - Technical Report).

Towards learning from stories: An approach to interactive machine learning

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this