Generating believable stories in large domains

Bilal Kartal, John Koenig, Stephen J. Guy

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

2 Scopus citations

Abstract

Planning-based techniques are a very powerful tool for automated story generation. However, as the number of possible actions increases, traditional planning techniques suffer from a combinatorial explosion due to large branching factors. In this work, we apply Monte Carlo Tree Search (MCTS) techniques to generate stories in domains with large numbers of possible actions (100+). Our approach employs a Bayesian story evaluation method to guide the planning towards believable stories that reach a user defined goal. We generate stories in a novel domain with different type of story goals. Our approach shows an order of magnitude improvement in performance over traditional search techniques.

Original languageEnglish (US)
Title of host publicationIntelligent Narrative Technologies - Papers from the 2013 AIIDE Workshop, Technical Report
PublisherAI Access Foundation
Pages30-36
Number of pages7
ISBN (Print)9781577356363
StatePublished - Jan 1 2013
Event9th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2013 Workshop - Boston, MA, United States
Duration: Oct 14 2013Oct 15 2013

Publication series

NameAAAI Workshop - Technical Report
VolumeWS-13-21

Other

Other9th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2013 Workshop
Country/TerritoryUnited States
CityBoston, MA
Period10/14/1310/15/13

Fingerprint

Dive into the research topics of 'Generating believable stories in large domains'. Together they form a unique fingerprint.

Cite this