Skip to main content

Big Data Algorithm for Customizing Video Game Difficulty

Read the Georgia Tech press release.

Georgia Tech researchers have developed a computational model that can predict video game players’ in-game performance and provide a corresponding challenge they can beat, leading to quicker mastery of new skills. The advance not only could help improve user experiences with video games but also applications beyond the gaming world. More...

Research Awards

The Entertainment Intelligence Lab racks up some Institute awards:

  • Dr. Steve Lee-Urban wins Outstanding Research Scientist in the College of Computing.
  • Undergrads George Johnston and Eric Fruchter both won People's Choice Awards for undergrad research projects. George's work is on crowdsourced natural language clustering. Eric's work is on learning optimal computer game parameters.
  • 6th Workshop on Intelligent Narrative Technologies

    The 6th Workshop on Intelligent Narrative Technologies will be held October 14-15, 2013 in conjunction with AIIDE'13. INT6 is co-organized in Entertainment Intelligence Lab member, Alex Zook.

    Papers are due July 3, 2013. See the call for papers.

    AAAI'13: Story Generation with Crowdsourced Plot Graphs

    Story Generation with Crowdsourced Plot Graphs, to appear at the AAAI Conference on Artificial Intelligence, July 2013.

    We present a novel class of story generation system that can generate stories in an unknown domain by (a) automatically learning a domain model via crowdsourcing and (b) sampling stories from the space defined by the domain model. A large-scale evaluation shows that stories generated by our system for a previously unknown topic are comparable in quality to simple stories authored by untrained humans.

    WeQuest available for download

    The WeQuest game engine and authoring tool are now available for download.

    WeQuest is a platform for authoring, sharing, and delivering mobile Alternate Reality Games (ARGs) in which geo-location is used to blend real world locations and fictional storyline elements...

    Creativity Support for Novice Digital Filmmaking

    Creativity Support for Novice Digital Filmmaking, Proceedings of CHI'13.

    Machinima is a new form of creative digital filmmaking that leverages the real time graphics rendering of computer game engines. Can novice machinima creators benefit from creativity support tools? We show that novices generally have difficulty adhering to cinematographic conventions and identify cinematic conventions novices typically violate. We report on a Wizard-of-Oz study showing a rule-based intelligent system can reduce the frequency of errors that novices make...

    The Intelligent Narrative Technologies workshop series

    The Intelligent Narrative Technologies workshop series was started in 2007 by Mark Riedl and Brian Magerko as a venue venue for emerging, high-quality research on the role of intelligent systems in creating, understanding, and interactive management of narratives. After five successful iterations, the workshop series is going strong. We look forward to INT 6 in 2013! The list of workshops/symposia and online proceedings follows...

    Interactive Narrative: An Intelligent Systems Approach

    Interactive Narrative: An Intelligent Systems Approach, AI Magazine, vol. 34(1), 2013.

    Interactive narrative is a form of digital interactive experience in which users create or influence a dramatic storyline through their actions. The goal of an interactive narrative system is to immerse the user in a virtual world such that he or she believes that they are an integral part of an unfolding story and that their actions can signi cantly alter the direction and/or outcome of the story. We review the ways in which arti ficial intelligence can be brought to bear on the creation of interactive narrative systems...

    Crowdsourcing Narrative Intelligence

    Crowdsourcing Narrative Intelligence. Advances in Cognitive Systems, vol. 2, 2012.

    Narrative intelligence is an important part of sensemaking and communicating with people.
    Humans draw on a lifetime of relevant experiences from which to explain stories, to tell stories, and to help choose the most appropriate actions in real-life settings. While this knowledge can be encoded in the form of rules, facts, or scripts, manual authoring presents a significant bottleneck in the creation of systems demonstrating narrative intelligence. In this project, we are developing a technique for automatically learning script-like narrative intelligence knowledge, particularly sociocultural knowledge, from human crowdsourcing. By leveraging the crowd and its collective understanding of social constructs, we can learn a potentially unlimited range of scripts regarding how humans generally believe real-world situations unfold.

    AI Grand Challenges involving story and creativity

    I've started a list of AI Grand Challenges that can only be solved by AI systems that can reason about story, creativity, and aesthetics. I'll be adding to the list over time. Most of my AI Grand Challenge ideas are also on twitter @mark_riedl, where I aggregate them on Storify. Feel free to send me your own ideas via email or tweet.

    Syndicate content