|
About EIS → |
Play against the EISBot! Download here: http://eis.ucsc.edu/sites/default/files/eisbot.zip
THE EISBot in a Protoss versus Terran match
So far, I’ve tested the bot versus the avid StarCraft fanbase. It pulls out a 10% win rate versus hardcore gamers. Can you beat it? Play it and send me the replay!!!
Note: playing against the EISBot requires two machines capable of playing StarCraft.
It doesn't look like the apocolypse
The title: Farmville Killed Gaming, V-Worlds, And Your Dog (tongue-in-cheek)
The premise: “…it seems the talk of GDC 2010 was… Farmville. Specifically, how metrics-driven game design (such as what Farmville uses) will destroy fun as we know it.”
The response: “i take particular exception to your statements about killing dogs. zynga is a dog loving company named after my dearly departed dog zinga.” (Mark Pincus, CEO of Zynga)
Other luminaries, such as Raph Koster, wade into the discussion at the comments thread at Broken Toys.
For what it’s worth, I personally agree with Jennings’ conclusion that games aren’t cannibalizing themselves as we know them in order to cater to new markets. I think metrics-driven development is a useful, exciting tool that helps developers better understand their audience. No-one can ever claim Zynga’s game lineup is not catering to some segment of society. Just because we’re used to The West Wing, doesn’t mean other people can’t enjoy American Idol, whatever you think of it.
I developed a version of EISBot that plays a specific strategy, known as a 10-15 gate rush. The build was recently made famous by Nony. It is a Protoss build with the goal of harassing your opponent with ranged units as fast as possible and is most commonly used against Terran opponents. This strategy requires a large number of micro-management actions to maximize the efficiency of each unit. This is achieved by attacking enemy units and then backing off.
I tested the bot against several human players on the International Cyber Cup and was surprised to discover that the bot achieved a win rate of over 30% when tested in 40 matches.
Protoss versus Protoss (EISBot at 7 O’ clock)
Protoss versus Terran (EISBot at 11 O’ clock)
Protoss versus Zerg (EISBot at 7 O’ clock)
Ken Perlin, Professor of Computer Science, New York University
Ken is giving a talk titled:
“Graphics, Games, Characters and Touchpads — a tour of recent research”
Date: Tuesday, March 16
Time: 11:00am
Place: E2-180 (The Simularium)
Abstract
This talk will provide an overview of various recent
research,mincluding Games for Learning, pressure sensitive touch
devices, emotively expressive procedurally animated characters,
intuitive 3D modeling, and ideas about bridging the divide between
programmers and non-programmers.
Ken Perlin's Responsive Face demo.
Bio
Ken Perlin is a professor in the Department of Computer Science at
New York University, directs the NYU Games For Learning Institute. He
was also founding director of the Media Research Laboratory and director
of the NYU Center for Advanced Technology. His research interests
include graphics, animation, user interfaces, science education and
multimedia. He received an Academy Award for Technical Achievement from
the Academy of Motion Picture Arts and Sciences for his noise and
turbulence procedural texturing techniques, which are widely used in
feature films and television, as well as the 2008 ACM/SIGGRAPH Computer
Graphics Achievement Award, the TrapCode award for achievement in
computer graphics research, the NYC Mayor’s award for excellence in
Science and Technology and the Sokol award for outstanding Science
faculty at NYU, and a Presidential Young Investigator Award from the
National Science Foundation. He has also been a featured artist at the
Whitney Museum of American Art. Dr. Perlin received his Ph.D. in
Computer Science from New York University, and a B.A. in theoretical
mathematics from Harvard University. Before working at NYU he was Head
of Software Development at R/GREENBERG Associates in New York, NY. Prior
to that he was the System Architect for computer generated animation at
Mathematical Applications Group, Inc. He has served on the Board of
Directors of the New York chapter of ACM/SIGGRAPH, and currently serves
on the Board of Directors of the New York Software Industry Association.
One of Kevin Dill's game credits: Master of Orion 3
“The Art of Game AI: Sculpting Behavior with Data, Formulas, and Finesse”
Kevin Dill, Lockheed Martin
Date: Monday, March 15
Time: 11:00am – 12:00pm
Place: E2-180 Simularium
Hosted By: Michael Mateas
Abstract
This lecture will explore the challenges that are involved in constructing believable AI behavior, the mindset that one must adopt to accurately model these behaviors, and the techniques that can be used to construct them. The attendee will leave with a broad summary of how to approach the artistry of constructing artificial behaviors – and will likely have adopted the annoying habit of assigning values and formulas to everything they see around them.
Biography
Kevin Dill has 9 years experience in the games industry as an AI developer and AI lead. He has 7 game credits, including Master of Orion 3, Axis and Allies, Zoo Tycoon 2: Endangered Species, and Iron Man. He now works at Lockhead Martin, where he develops AI for training simulations that include a mix of live acting, mixed and augmented reality, and even animatronics. Kevin has a BA in Computer Science from Carleton College and an MS in Computer Science from Northwestern University.
The CNET News article, GDC: What’s next for video game AI?, features demos of EIS research projects delivered at the AI Summit at GDC along with the latest AI demos from Richard Evans and Ian Holmes. The AI Summit session, Experimental Game AI: Live Demos of Innovation, included demos of EIS’s Starcraft agent and The Prom, a system featuring play in social space.
A demo of The Prom, or Promacolypse, was given by Michael Mateas at GDC's AI Summit.
A demo of the Starcraft bot was given at GDC's AI Summit.
