I admit it. I have never been a good reader. Hmm, yet I like to blog. Oh Well.
That being said, some of the only books that I had time for when I was little were “Choose Your Own Adventure”. To me, it was like I was playing a video game in my mind.
Yes, I was one that kept my place in the book, you know, in case I died. Shame on me right! I would also re-read them time and time again to see how many stories I could make happen.
Researchers at the Georgia Institute of Technology have created the first AI that can create Choose Your Own Adventures. This is not the first time that an AI has created multiple outcome scenarios. The first time that Crowdsourcing has been used to assist in the creation of such a wonderful tale.
Plot points are collected from human users on the crowdsourcing platform Amazon Mechanical Turk. The AI then takes this info and create the basic events by taking the info from the plot points and locations and identifying typical event ordering.
“Our open interactive narrative system learns genre models from crowdsourced example stories so that the player can perform different actions and still receive a coherent story experience,” said lead investigator Mark Riedl, an associate professor of interactive computing at Georgia Tech.
“When enough data is available and that data sufficiently covers all aspects of the game experience, the system was able to meet or come close to meeting human performance in creating a playable story.”
How did they test? Well it was intresting to read. According to CNet:
The team tested the AI on two story scenarios, a bank robbery and a movie date, pitting its creations against sets of stories by a human programmed generator and a random generator.
Human test subjects were then divided into three groups. One group read the Scheherazade stories, the second group read the human generator stories, and a third group read the random generator stories.
The groups were tasked with looking for errors, or scenes placed out of sequence. They also had to rate the stories based on their own enjoyment, and how coherent they found them.
The poor old random generator performed poorly in both scenarios, but Scheherazade did almost as well as the human generator. For the bank robbery story, players reported a median of three errors for both the human and AI, while the random generator had a median of 12.5 errors. For the movie date story, the human generator had median of three errors reported, the AI had five, and the random generator had 15.
Additionally, the groups reported similar levels of satisfaction with both the human and Scheherazade stories, indicating they were more or less equally coherent, enjoyable and engaging.
The next step is making the stories deeper and more entertaining. The human writers still hold the market on that.
Still, it is interesting to see what the future will hold for the AI Experience. As we advance, what will become normal.