Home About EIS →

UCSC Hosts Symposium on Narrative Intelligence: AI Approaches for Games and Fiction

DATE: October 14th, 2010 — 9:30am to 5:30pm

LOCATION: UCSC Campus, Engineering 2, Room 599
PRICE: Free (though UCSC parking pass required)
HOSTED BY: The UCSC Center for Games and Playable Media. Co-sponsored by the Digital Arts and New Media program and Institute for Humanities Research.

Symposium Topic

What would it take for computer games and digital literature to dynamically offer meaningful story choices based on past interactions, or draw analogies inspired by authors such as Virginia Woolf, or create avatars that are meaningful characters with individual motivations, or give us new means to understand the phenomena of narrative itself? Any of these would require research into fundamentally new computational models — but research that is deeply informed by insights of the arts, humanities, and social sciences. This free, one day symposium (the first event sponsored by the new UC Santa Cruz Center for Games and Playable Media) brings together four leading international researchers with UCSC’s active research groups in this area.

Read More »

Posted in Academics | Comments closed

Brian Lande at UCSC

Brian Lande
“‘When You Are Strange’: Mutual Intelligibility, Intercoporeality, and Accountability in Stranger Encounters”
Brian Lande, Ph.D, Program Manager, DARPA, Arlington VA

Date: Thursday, September 30, 2010
Time: 11:00 am
Place: Engineering 2 Room 399

This lecture is free and open to the public, but visitors should purchase a parking pass from the visitor kiosk at the main entrance. There they can also provide a map showing the best parking for the School of Engineering.

Abstract:
This talk provides a preliminary theoretical framework for understanding how individuals who come from different backgrounds and little in the way of shared knowledge, language, history, experience, and embodied forms of life (habitus) encounter one another. The talk draws on four years of ethnographic observation while working as a deputy sheriff in Santa Cruz County as well as touches on the similar challenges that now face state department officials and military personnel in the constabulary like context of Counter Insurgency operations. I argue that current conceptions of culture and cross cultural competency are inadequate for understanding stranger encounters, why some people are “good strangers”, and how to teach people how to move across vast social chasms. For young policemen, aid workers, and soldiers, alike, how stranger encounters are approached, oriented to, and managed is frequently fatal and consequential.

Bio:
Dr. Lande joined DARPA as a Program Manager in June 2010. His research interests include the study of aggression and violence in groups and across cultures, how people manage their emotions in social settings, use of force training, ethnomethodology/microsociology, social perception, qualitative data collection and analysis, and methods of visually mapping social relationships.

Prior to joining DARPA, Dr. Lande was a deputy sheriff in California and a doctoral candidate in sociology at the University of California, Berkeley. His prior research focuses on use of force training, military and law enforcement socialization, and the role of the body and emotion in communication and social action. As a deputy sheriff, Dr. Lande participated in a wide range of law enforcement practices and training including: felony and misdemeanor investigations, coroner’s investigations, interview and interrogation, patrol, drug interdiction, writing and serving search warrants, high risk entries, and financial crimes investigations.

Dr. Lande received Ph.D. and M.A. degrees in Sociology from the University of California, Berkeley in 2010 and 2005, respectively, and B.S. (Psychology) and B.A. (Philosophy) degrees from Montana State University – Bozeman.

Posted in Academics | Comments closed

Making Sense with Answer Set Programming: “I’m into nuggets ya’ll”

I’m currently working on modeling stories through Answer Set Programming. My last research post was about using retroactive continuity in storytelling as rationalization mechanisms (defined by Abelson’s Goldwater Machine or my adviser’s Terminal Time) for story explanation. As more work goes into using logic programming in representing stories and characters, there are snags along with moments of small novel discoveries. Yesterday, Adam Smith was helping me work out a few snags in the event calculus for this story system. Overall, I want to anecdotally describe what working with believability in technology and expressive intelligence is like, along with giving some insights on formal models of story.

Read More »

Posted in Academics | Comments closed

Infinite Adaptive Mario

Recently, there has been increased interest in building games that dynamically adapt to players. One of the common approaches to building adaptive games is dynamic difficulty adjustment. However, most of these approaches are limited to parameter tweaking such as adjusting weapon strength or reducing spawning times, and do not modify levels in response to difficulty adjustment. My system attempts to overcome this limitation by incorporating parameter tweaking into procedural content generation. The system creates new levels on the fly in response to the current performance of the player.

Infinite Adaptive Mario expands on Markus Persson’s Infinite Mario by adapting to the skill of the player. A description of the level generator used by the system is provided here. One of the inputs to the system is a set of parameters which specify probabilities for specific events to occur, such as placing a gap. By modifying these probabilities, the system can create a large space of levels with varying difficulty. Infinite Adaptive Mario scales up difficulty by increasing the frequently of gaps, average size of gaps, variation of ground height, and number of enemies. Scaling up the difficulty also tends to result in a larger number of possible paths through a level.

A level generated at the easiest difficulty

Read More »

Posted in Academics | Tagged , , , , , , , , | Comments closed

Retrospective on the CIG 2010 Level Design Competition

At the recent 2010 Computational Intelligence in Games conference in Copenhagen, Denmark, there were competitions for making race car controllers, human-like FPS bots, and Ms. Pac Man players, among others. The competition that drew my interest, however, was the Mario level design competition, which challenged entrants to create procedural level generators that could generate fun and interesting levels based on information about a particular player’s style. The restrictions on entries (use only fixed numbers of gaps, coin blocks, and Koopas) meant that the winner would have to be cunning: it wouldn’t be easy to just estimate player skill and make the level more or less difficult by adding or removing obstacles; you would instead have to find ways to place obstacles that made the same obstacles more or less difficult. And because entries would be played by players at different skill levels, they would have to be flexible and adjust their output over a broad range of difficulties to get a high score. Finally, because score was based on the audience’s relative rating of enjoyment between level pairs, there would be no way to game the system and optimize some metric set without making truly enjoyable levels. Between these constraints, the winning entry should have been a demonstration of the power of procedural content generation to adapt to players of different skill levels, which is one of several reasons that PCG is useful in games. Unfortunately, the competition design may have been a bit too clever.

Read More »

Posted in Academics | Comments closed

A Probabilistic Multi-Pass Level Generator

I recently participated in the CIG 2010 Mario level generation competition. My submission utilizes a multi-pass approach to level generation in which the system iterates through the level several times, placing different types of objects during each pass. During each pass through the level, a subset of each object type has a specific probability of being added to the level. The result is a computationally efficient approach to generating a large space of randomized levels.

A level created by the probabilistic multi-pass generator

Read More »

Posted in Academics | Comments closed