Show simple item record

dc.contributor.advisorRiedl, Mark O.
dc.contributor.authorDass, Nathan
dc.date.accessioned2018-08-20T19:10:37Z
dc.date.available2018-08-20T19:10:37Z
dc.date.created2017-12
dc.date.submittedDecember 2017
dc.identifier.urihttp://hdl.handle.net/1853/60341
dc.description.abstractStorytelling has applications in areas ranging from creating books and novels to engrossing movie scripts to the gaming industry. It would be useful to create interactive plot lines for games, motivate mission generation, and ordering of events for different characters. In the military, we can make the system learn from thousands of written real-world events, incidents, and missions to create interactive simulations to train army personnel. We introduce a deep reinforcement learning approach to story generation trained on a textual story corpus. Unlike other neural network based approaches to story generation, a reward function allows a human user to control the direction that the story follows.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectNatural language processing
dc.subjectDeep reinforcement learning
dc.subjectLanguage modeling
dc.subjectStory generation
dc.titleStory Generation with Deep Reinforcement Learning
dc.typeUndergraduate Research Option Thesis
dc.description.degreeUndergraduate
dc.contributor.departmentComputer Science
thesis.degree.levelUndergraduate
dc.contributor.committeeMemberIsbell, Charles L
dc.contributor.committeeMemberBatra, Dhruv
dc.date.updated2018-08-20T19:10:37Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record