Eating an octopus tentacle in Hakodate, Japan, May 2006
Mark J. Nelson
mnelson@cc (.gatech.edu)
Hi! I'm a PhD student in computer science, working in artificial intelligence.
My dissertation is on automated support for game design. I'm building a tool
that helps designers prototype their gameplay rules by applying
automated-reasoning techniques to them, using a logical formalism for reasoning
about time-varying systems, the event calculus. The goal is to be able to let
designers query a set of rules instead of manually working out its
implications, answering design questions ranging from debugging to
brainstorming to game balancing. It's turning out to be about equal parts
technical work in logic to develop event-calculus programming and inference
tools, ethnographic interviews with game designers to understand how they work
and how they might use a tool like this, and interface building to make the
logical machinery usable by non-logicians.
I'm working in Michael
Mateas's Expressive Intelligence Studio (EIS), now located at the
University of California, Santa Cruz. I've at various times collaborated with
Charles Isbell and his pfunk research group.
I also do work on interactive narrative, and longer ago did some on the
periphery of computer music. Lurking in the todo pile is some
as-yet-unpublished stuff on machine learning, mainly local regression methods
and regression forests. In my allegedly free time, I'm a Wikipedia sysop/administrator and frequent
editor.
I'm building a game-design assistant to help designers prototype their rule
systems; see description above. The AIIDE paper is the one most directly on
that subject.
In addition to the game-design assistant, a few of these papers explore other
aspects of representing and reasoning about games. The AI*IA and IUI papers
propose factoring game design into four areas: abstract mechanics, concrete
representation, thematic (real-world) references, and player input. They
additionally do some early work in reasoning about real-world references, e.g.
for automatically generating "skinned" versions of games. The IUI paper also
more generally argues for the usefulness of reasoning about real-world
references in an interactive game-design assistant.
Mark J. Nelson and Michael Mateas. Recombinable game mechanics for automated design
support.
In Proceedings of the 4th Artificial Intelligence and Interactive Digital
Entertainment Conference (AIIDE 2008), Palo Alto, California, USA,
October 2008.
Mark J.
Nelson and Michael Mateas. An interactive game-design assistant.
In Proceedings of the 2008 International Conference on Intelligent User
Interfaces (IUI 2008), pages 90–98, Maspalomas, Gran Canaria,
Spain, January 2008.
Mark J.
Nelson and Michael Mateas. Towards automated game design.
In AI*IA 2007: Artificial Intelligence and Human-Oriented
Computing, pages 626–637. Springer, 2007.
Lecture Notes in Computer Science 4733.
Declarative Optimization-Based Drama Management (DODM)
Drama managers watch a game (or other interactive experience) as it progresses,
and intervene when necessary to keep the experience interesting and in line
with an author's goals. DODM is a particular approach in which an author
declaratively specifies what it would mean for the experience to go well, along
with an abstraction of the story and a set of interventions the system can
make. The system then optimizes its interventions according to the given
criteria.
The basic approach was proposed by Joe Bates in 1992 and developed by Peter
Weyhrauch in 1997. We've since made a number of modifications, both to the
conceptual formulation and to the technical implementation.
Sherol
Chen, Mark J. Nelson, Anne Sullivan, and Michael Mateas. Evaluating the authorial leverage of drama management.
In Working Notes of the AAAI Spring Symposium on Intelligent Narrative
Technologies, Palo Alto, California, USA, March 2009.
Mark J.
Nelson and Michael Mateas. Another look at search-based drama management.
In Proceedings of the 23rd AAAI Conference on Artificial
Intelligence, Chicago, USA, July 2008.
A shorter version appeared in the proceedings of AAMAS 2008.
Sooraj Bhat,
David L. Roberts, Mark J. Nelson, Charles L. Isbell, Jr., and Michael
Mateas. A globally optimal algorithm for TTD-MDPs.
In Proceedings of the 6th International Joint Conference on Autonomous
Agents and Multiagent Systems (AAMAS 2007), Honolulu, Hawaii, USA,
May 2007.
David L.
Roberts, Mark J. Nelson, Charles L. Isbell, Jr., Michael Mateas, and
Michael L. Littman. Targeting specific distributions of trajectories in MDPs.
In Proceedings of the 21st National Conference on Artificial Intelligence
(AAAI 2006), Boston, USA, July 2006.
I evaluated MIDI performance as part of previous work (2003–2004)
with Belinda Thom at Harvey Mudd College. We were trying to
discover interesting things about jazz improvisation, but got
sidetracked into measuring the performance of our MIDI equipment,
since we needed to be able to put error bars on the data. You may
also want to take a look at the project's
site, which has code, circuit diagrams, and everything else you
need to run your own tests, as well as the detailed results of our
tests.
Mark J.
Nelson and Belinda Thom. A survey of real-time MIDI performance.
In Proceedings of the 2004 International Conference on New Interfaces for
Musical Expression (NIME 2004), pages 35–38, Hamamatsu, Japan, June
2004.
