Why AI Should Read and Write Stories

Submitted by Mark Riedl on Wed, 10/14/2015 - 21:57
This short blog post in Huffington Post discusses the virtues of AI that has narrative intelligence---the ability to understand, read, and write stories.

AI Creates Super Mario Bros. Levels

Submitted by Mark Riedl on Tue, 09/15/2015 - 12:43

Matthew Guzdial and the Entertainment Intelligence Lab has developed an intelligent system that watches people play Super Mario Bros. and learns how to generate novel game levels from scratch. Read the press release.

A Game Engine for teaching Game AI

Submitted by Mark Riedl on Tue, 09/15/2015 - 12:38

The Game AI Game Engine was developed to help teach Game AI. It provides an extensible, Python game engine and a series of programming assignments that explores many of the ways AI is used in games. The series of programming assignments builds toward a complete, playable MOBA game, giving students a sense of progression and accomplishment.

GAIGE is available for free download!

EI Lab at Foundations of Digital Games 2015

Submitted by Mark Riedl on Mon, 06/08/2015 - 10:22

We have four papers at the 2015 International Conference on Foundations of Digital Games.

Main conference papers:

  • Crowdsourcing Open Interactive Narrative by Matthew Guzdial, Brent Harrison, and Boyang Li.
  • Monte-Carlo Tree Search for Simulation-based Strategy Analysis by Alex Zook and Brent Harrison.

    • Procedural Content Generation workshop papers:

  • Toward Game Level Generation from Gameplay Videos by Matthew Guzdial.
  • Automatic Generation of Game-based CAPTCHAs by Hong Yu.

    • Data-Driven Drama Management

    Submitted by Mark Riedl on Wed, 05/13/2015 - 10:16

    Interactive narrative is a form of digital interactive experience in which users create or influence a dramatic storyline through actions, either by assuming the role of a character in a fictional virtual world, issuing commands to computer-controlled characters, or directly manipulating the fictional world state. Hong Yu's thesis describes how to use data about players' preferences to control the flow of players' individual experiences.

    Thesis on Scheherazade

    Submitted by Mark Riedl on Fri, 01/09/2015 - 15:00

    Boyang "Albert" Li's thesis is now available here. Albert describes the technique behind the Scheherazade system, which learns narrative intelligence from an online crowd, and uses it to generate and understand stories.

    An alternative to the Turing Test

    Submitted by Mark Riedl on Thu, 10/23/2014 - 10:19

    Observing that the creation of certain types of artistic artifacts necessitate intelligence, we have designed the Lovelace 2.0 Test of creativity as an alternative to the Turing Test. The Lovelace 2.0 Test builds off prior tests of creativity and additionally provides a means of directly comparing the relative intelligence of different agents. 2 page PDF at arXiv

    EI Lab at AAAI'14

    Submitted by Mark Riedl on Fri, 05/09/2014 - 11:26

    The Entertainment Intelligence Lab is doing it's best to turn AAAI'14 into a games and entertainment conference. We have two papers:

  • Automatic Game Design via Mechanic Generation by Alex Zook
  • Dramatis: A Computational Model of Suspense by Brian O'Neill

    • Mark Riedl promoted!

    Submitted by Mark Riedl on Wed, 03/12/2014 - 19:34

    Mark Riedl has been promoted to Associate Professor with Tenure.

    Mark Riedl receives NSF CAREER Award

    Submitted by Mark Riedl on Sat, 03/01/2014 - 01:24

    Mark Riedl received an NSF CAREER Award for his proposal, Combining Crowdsourcing and Computational Creativity to Enable Narrative Generation for Education, Training, and Healthcare.

    Syndicate content