Efficient intent-based narrative generation using multiple planning agents

J. (Jonathan) Teutenberg, J. (Julie) Porteous

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearch

Abstract

In Interactive Storytelling (IS) the prevailing approach for the automatic generation of plausible narratives that meet global author goals is intentional planning. However, existing approaches suffer from limited expressiveness and poor scalability. We address this by replacing single intentional planners with multiple agents representing the characters of a narrative, which can reason about the relevance of narrative actions given their individual intents. These are then combined using a state-based forward search procedure that results in a significantly smaller search space.

Unlike other multiagent approaches, these agents calculate all reasonable plans in a state. This allows a search of a wide range of narrative possibilities prior to execution as in planner-based approaches, rather than agents making early plan commitments in a simulation.

We demonstrate that this not only produces the same forms of narrative as single intentional planners but can be extended to generate narratives that are beyond their scope. We also present a search heuristic that exploits the agents' relevant actions to further reduce the size of the explored search space. Experimental results demonstrate system performance that makes it suitable for use in real-time applications such as IS.
Original languageEnglish
Title of host publicationProceedings of the 2013 international conference on Autonomous agents and multi-agent systems
Subtitle of host publicationAAMAS '13
Place of PublicationRichland, SC
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages603-610
ISBN (Print)9781450319935
Publication statusPublished - 2013
Event2013 International Conference on Autonomous Agents and Multi-agent Systems - St. Paul, United States
Duration: 6 May 201310 May 2013
Conference number: 13

Conference

Conference2013 International Conference on Autonomous Agents and Multi-agent Systems
Abbreviated titleAAMAS '13
CountryUnited States
CitySt. Paul
Period6/05/1310/05/13

Fingerprint

Planning
Scalability

Cite this

Teutenberg, J. J., & Porteous, J. J. (2013). Efficient intent-based narrative generation using multiple planning agents. In Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems : AAMAS '13 (pp. 603-610). Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).
Teutenberg, J. (Jonathan) ; Porteous, J. (Julie). / Efficient intent-based narrative generation using multiple planning agents. Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems : AAMAS '13. Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2013. pp. 603-610
@inproceedings{fb7048e1e0404bdf83ee3ba4e6033449,
title = "Efficient intent-based narrative generation using multiple planning agents",
abstract = "In Interactive Storytelling (IS) the prevailing approach for the automatic generation of plausible narratives that meet global author goals is intentional planning. However, existing approaches suffer from limited expressiveness and poor scalability. We address this by replacing single intentional planners with multiple agents representing the characters of a narrative, which can reason about the relevance of narrative actions given their individual intents. These are then combined using a state-based forward search procedure that results in a significantly smaller search space.Unlike other multiagent approaches, these agents calculate all reasonable plans in a state. This allows a search of a wide range of narrative possibilities prior to execution as in planner-based approaches, rather than agents making early plan commitments in a simulation.We demonstrate that this not only produces the same forms of narrative as single intentional planners but can be extended to generate narratives that are beyond their scope. We also present a search heuristic that exploits the agents' relevant actions to further reduce the size of the explored search space. Experimental results demonstrate system performance that makes it suitable for use in real-time applications such as IS.",
author = "Teutenberg, {J. (Jonathan)} and Porteous, {J. (Julie)}",
year = "2013",
language = "English",
isbn = "9781450319935",
pages = "603--610",
booktitle = "Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems",
publisher = "International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)",

}

Teutenberg, JJ & Porteous, JJ 2013, Efficient intent-based narrative generation using multiple planning agents. in Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems : AAMAS '13. International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), Richland, SC , pp. 603-610, 2013 International Conference on Autonomous Agents and Multi-agent Systems , St. Paul, United States, 6/05/13.

Efficient intent-based narrative generation using multiple planning agents. / Teutenberg, J. (Jonathan); Porteous, J. (Julie).

Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems : AAMAS '13. Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2013. p. 603-610.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearch

TY - GEN

T1 - Efficient intent-based narrative generation using multiple planning agents

AU - Teutenberg, J. (Jonathan)

AU - Porteous, J. (Julie)

PY - 2013

Y1 - 2013

N2 - In Interactive Storytelling (IS) the prevailing approach for the automatic generation of plausible narratives that meet global author goals is intentional planning. However, existing approaches suffer from limited expressiveness and poor scalability. We address this by replacing single intentional planners with multiple agents representing the characters of a narrative, which can reason about the relevance of narrative actions given their individual intents. These are then combined using a state-based forward search procedure that results in a significantly smaller search space.Unlike other multiagent approaches, these agents calculate all reasonable plans in a state. This allows a search of a wide range of narrative possibilities prior to execution as in planner-based approaches, rather than agents making early plan commitments in a simulation.We demonstrate that this not only produces the same forms of narrative as single intentional planners but can be extended to generate narratives that are beyond their scope. We also present a search heuristic that exploits the agents' relevant actions to further reduce the size of the explored search space. Experimental results demonstrate system performance that makes it suitable for use in real-time applications such as IS.

AB - In Interactive Storytelling (IS) the prevailing approach for the automatic generation of plausible narratives that meet global author goals is intentional planning. However, existing approaches suffer from limited expressiveness and poor scalability. We address this by replacing single intentional planners with multiple agents representing the characters of a narrative, which can reason about the relevance of narrative actions given their individual intents. These are then combined using a state-based forward search procedure that results in a significantly smaller search space.Unlike other multiagent approaches, these agents calculate all reasonable plans in a state. This allows a search of a wide range of narrative possibilities prior to execution as in planner-based approaches, rather than agents making early plan commitments in a simulation.We demonstrate that this not only produces the same forms of narrative as single intentional planners but can be extended to generate narratives that are beyond their scope. We also present a search heuristic that exploits the agents' relevant actions to further reduce the size of the explored search space. Experimental results demonstrate system performance that makes it suitable for use in real-time applications such as IS.

M3 - Conference contribution

SN - 9781450319935

SP - 603

EP - 610

BT - Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems

PB - International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)

CY - Richland, SC

ER -

Teutenberg JJ, Porteous JJ. Efficient intent-based narrative generation using multiple planning agents. In Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems : AAMAS '13. Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS). 2013. p. 603-610