Tag: artificial intelligence

References from a talk on AI and procedural narrative

Last night I spoke to the Oxford AI Meetup about a variety of work going around artificial intelligence and (especially) game narrative. We talked about simulation-based and narrative-model based approaches to plot generation, agent-driven stories, dialogue selection and generation, and natural language understanding, with an emphasis on relatively recent or ongoing research projects and released games. (So I didn’t do a deep dive into the history of narrative generators.)

At the end of the talk, several people asked for links to the things I’d mentioned, so here they are:

Games and projects:

Dwarf Fortress and other dwarflikes
Talk of the Town (James Ryan et al) (or if the paper is a bit dense, you might also like Games by Angelina’s writeup of the core concepts)
IDtension / Nothing for Dinner (Nicolas Szilas et al); I discussed it a bit
Scheherazade project (Mark Riedl et al, Entertainment Intelligence Lab, Georgia Tech) using crowd-sourced event descriptions to generate a graph of possible story developments
Restaurant Game (Jeff Orkin et al)
Dear Leader’s Happy Story Time (Ian Horswill, relatively new/early but I thought an interesting contrast)
Ice-Bound Concordance (Aaron Reed and Jacob Garbe)
Event[0]
Firewatch (see also my review)

My own work:

Galatea (and this article on translating Galatea to Versu)
Versu and Blood & Laurels
Annals of the Parrigues (and other discussion about procedural text generation)

Other talks, tools, and resources that were mentioned in the talk or in subsequent Q/A time:

Elan Ruskin’s GDC talk on salience mechanism
Kate Compton’s easy CFG tool Tracery
My Beyond branching narratives post
80 Days (came up in discussion about player agency and visible mechanics)

Nothing for Dinner (Nicolas Szilas et al, IDtension)

IDtension_conversation_menu.png

“Nothing for Dinner” is an interactive drama released last fall by Nicolas Szilas and collaborators, using a tool called IDtension. Szilas works out of the TECFA Lab at the University of Geneva. If you read my writeup on the book Interactive Digital Narrative, you’ll have seen a mention of Szilas’ article there. Though it would have been out of place in the book overview, I wanted to come back and look more closely at what “Nothing for Dinner” accomplishes.

The premise of the story is that you’re a young man whose father has suffered a stroke that affects his behavior and memory. You need to get something ready for dinner, but your father keeps getting in the way, and other events spontaneously happen — a school friend coming over to get back a textbook she left at your house, your sister’s DVD player breaking, a phone call from your mother with extra chores — to add blocks to your progress.

The system is clearly quite dynamic: I played three times, and the sequence of events was very different each time, with some blockers appearing only in one of the playthroughs. Also, the conversation menus are dynamically generated to let you try various approaches to any of the currently-active problems, or to give emotional feedback to the other characters about what they’ve just done.

IDtension_grandma.png

If you try to cook dinner alone, your father resentfully complains that you never want to do anything with him; if you try to involve him, he may get annoyed and refuse to help you; if you let him cook by himself, he’ll break things and make a mess. And whenever your father gets upset, your grandmother comes over to chide you for not looking after him.

It’s a very effective mechanism for making me rapidly resent my entire family for offloading all the emotional and practical labor onto me: like a time management game, but with more passive-aggressive commentary, and less opportunity to get anything done.

Continue reading “Nothing for Dinner (Nicolas Szilas et al, IDtension)”