Game AI as Storytelling

I created a short screencast based on a very interesting paper on Game AI as Storytelling, which was produced from Georgia Tech’s Intelligent Narrative Computing group.  Imagine if you lived in the world of Little Red Riding Hood (or Rotkäppchen for purists), where you can kill random characters.  How many variations of the story can there be?  Well, if you limit yourself to 5 killings, there are over 1300 branches.  I won’t give too much away, but some stories involve a fairy and a new character called Grendel…  My short presentation hardly does the paper justice, but serves as a very high-level overview.

The screencast is in two parts: part 1 and part 2.  My mic sensitivity was set too high for part 1, so please make sure your volume isn’t too loud!  Here are my slides, which I created with the LaTeX Beamer class.  This was my first presentation made with Beamer, and it was a great experience.  Forget PowerPoint!  Beamer allows me to draft a presentation from pure text, in Emacs, and use LaTeX.  Brilliant!

So, I tormented some friends with playing an interactive fiction game with a drama manager based off of this published work.  It’s a subset of what the authors researched.  I decided to model player frustration, and as you can see, this is a frustrating game, even with hints! 🙂  To be fair to the player, the cause of most of the frustration was in the input system (natural language processing), which I didn’t try to resolve.

1200 Cycles is about 1 minute, the player played the game for about 1 hour

The next step is extend this with some procedural generated subplots, ala Skyrim.  If anybody wants to be a test subject (think Aperture Science), let me know and I’ll try to package up the game and instructions for returning the data.  There will be cake.