AI in new video games

A story in USA Today, AI is A-OK in new games, reviews the use of AI techniques in current video games, including Halo 3, Enemy Territory: Quake Wars, and Call of Duty 4: Modern Warfare.

“Our video-game enemies are smart — and getting smarter. The artificial intelligence that guides in-game characters today leads to far more natural actions and realistic friends and foes than in the past. “As graphics improvements top out, artificial intelligence will (drive) game innovation,” says University of California-Santa Cruz professor Michael Mateas.”

Of course, sometimes seeing all these games makes me think about how focused on warfare our culture is. Could the US industry produce a game like Katamari Damacy?

Posted in AI | No Comments »

Do computers play games like humans?

Ten years ago IBM’s Deep Blue beat then reigning world chess champion Gary Kasparov in an exhibition match under regular time control. So what does this mean — about the minds computers and people?

Noted Tufts philosopher Daniel Dennett has an article, Higher Games, in this month’s Technology Review in which he discuses the meaning of event.

“Chess requires brilliant thinking, supposedly the one feat that would be–forever–beyond the reach of any computer. But for a decade, human beings have had to live with the fact that one of our species’ most celebrated intellectual summits–the title of world chess champion–has to be shared with a machine, Deep Blue, which beat Garry Kasparov in a highly publicized match in 1997. How could this be? What lessons could be gleaned from this shocking upset? Did we learn that machines could actually think as well as the smartest of us, or had chess been exposed as not such a deep game after all?”

(spotted on AAAI’s AI in the News)

Posted in AI, General | 1 Comment »

Humans win first Man-Machine Poker Championship

This week the anual conference for the Association for the Advancement Artificial Intelligence (AAAI) hosted the First Man-Machine Poker Championship. A poker-playing computer program developed by researchers from the University of Alberta challenged two top-level poker professionals in a controlled scientific experiment with $50,000 of real money on the line. The game? Texas Hold ‘Em heads-up limit poker.

“The competition will consist of four 500-hand duplicate matches. In each duplicate match, the same series of cards will be dealt in two parallel Man versus Machine matches, with teammates playing the opposite hands in each game. At the end of the match, the total number of chips won or lost by each team is added together to determine the winning team. This format is used to reduce the element of random luck to a minimum, and get a much better indication of the differences in skill.

The human team of Phil Laak and Ali Eslami won two rounds out of three and hence the match.

Here’s the kickoff introduction by Jonathan Schaeffer from the University of Alberta and a post match interview with Phil and Ali

You can also read John Markoff’s story in the times, In Poker Match Against a Machine, Humans Are Better Bluffers. Ironically, that story appeared in the Times’ business section.

Posted in AI, technology | No Comments »

Checkers is a solved game

An article in Science by Jonathan Schaeffer and colleagues at the University of Alberta claims to have proven that checkers is a solved game — perfect play by both players will result in a draw. This is an amazing result!

“The game of checkers has roughly 500 billion billion possible positions (5 x 1020). The task of solving the game, determining the final result in a game with no mistakes made by either player, is daunting. Since 1989, almost continuously, dozens of computers have been working on solving checkers, applying state-of-the-art artificial intelligence techniques to the proving process. This paper announces that checkers is now solved: perfect play by both sides leads to a draw. This is the most challenging popular game to be solved to date, roughly one million times more complex than Connect Four. Artificial intelligence technology has been used to generate strong heuristic-based game-playing programs, such as DEEP BLUE for chess. Solving a game takes this to the next level, by replacing the heuristics with perfection.”

Access to the article requires a subscription, but you can access some online material for free. Better yet, you can see a video and 95 minute podcast of Schaeffer describing the Chinook program how they proved that checkers is a draw game. Amazingly, Shaeffer says that his programs that have been exploring the checkers game tree have been running, off and on, for eighteen years! Also, check out the article Computer Checkers Program Is Invincible in today’s New York Times.

Can you play a perfect game? To find out, you can try the Chinook program on-line.

Posted in AI | No Comments »

Game designers test the limits of AI

An article by Scott Kirsner in the Boston Globe, Game designers test the limits of artificial intelligence, talks about research aimed at improving massively multiplayer online games (MMOGs).

“A lot of the most interesting work in artificial intelligence is being done by game developers,” says Bruce Blumberg, senior scientist at Blue Fang Games in Waltham, and formerly a professor at MIT’s Media Lab. “You have really bright kids who are dealing with problems they don’t realize are insoluble. They’re very motivated.”

In MMOGs, most of the characters are intelligent because that are controlled by people, so the behavior of computer controlled characters compare badly. Another challenge of MMOGs is that the human-controlled characters interact largely through conversations in natural language.

“You can’t talk to characters and expect a response that feels real,” Davis says. “So there are no games that are like detective stories, or romances, which are popular genres in the movies, because you can’t interview suspects or talk to other people.” … One way to get there is by having humans “train” the AI software. That’s the approach that game designer Jeff Orkin, now a grad student at the Media Lab, is taking. With a project called The Restaurant Game, Orkin invites players to assume the role of a restaurant’s wait staff. His plan is to capture their behavior and dialogue, and use it to build more realistic software-driven characters, in the same way that designers sometimes use motion capture cameras to record and replicate human movement.

Posted in AI, MMOGs, social media | No Comments »

AI in games

The UK paper The Independent has a good article last week on the increasing need by industry for engineers who know AI concepts and techniques.

Artificial intelligence courses meet growing industry demands

Robots are being built to do our chores - and those who are creating them are already debating whether their rights should be recognized. Kate Hilpern reports
…
Most people don’t realize the extent to which AI is already used in our everyday lives, believes Browne. “For instance, AI is used in supermarkets to work out what products should be placed with other products, and whether certain products should be stacked vertically or horizontally. Companies invest a huge amount in AI in these kinds of ways to get people to spend a bit more money.” AI is also used to create robot technology to do things like construct our cars, clean our floors and even perform delicate microsurgery. Military and agricultural applications of AI are also on the rise and increasingly, AI is being used to assist disabled and elderly people. …

The game industry is another big application area for AI. The emphasis in the last decade has been on exploiting increased processor and GPU speeds to support more realistic graphics. Many think that using game AI to make game play and and the behavior of non-player characters more sophisticated and intelligent will become a significant discriminator in the next ten years.

The Independent article notes

“One of the fastest growing employers of AI graduates is the computer games industry. In fact, some universities run specific courses for people who want to work in this field. Gareth Bellaby, course leader for the BSc in computer games development at the University of Central Lancashire, says, ‘One of the most important aspects of all computer games is AI because, for instance, characters within the games need to be able to move around a map or landscape without bumping into walls - which is more difficult than it might sound - and make decisions against human opponents. Then there are challenges like ensuring that the camera can move around the landscape in a sensible fashion.’ Bellaby believes the computer games industry is the most fun end of AI. ‘It’s also one of those areas within AI where there are usually jobs available.’”

If you are interested in studying AI at UMBC there are many undergraduate courses to choose from, including principles of AI, machine learning, robotics, multiagent systems, natural language processing, neural networks, and various special topics courses.

Posted in AI, CS, UMBC classes | No Comments »

Making machines, and computer games, *really* intelligent

People are remarkably good at “muddling through”, at not getting completely stuck, at continuing to make some progress even when things don’t go as planned. Machines, on the other hand, tend to fail in dramatic fashion when they are faced with unusual circumstances.

UMBC professor Tim Oates is working on building more robust intelligent systems through metacognition, which is the ability to think about your own thinking. Meta-cognitive systems can notice when things are not going well (as opposed to just plowing ahead with whatever they were doing, which is what most systems do today), reason about possible sources of the problem, and try various repairs.

Professor Oates and his colleagues have constructed a meta-cognitive computer player for the tank game Bolo that learns from its mistakes and adapts its knowledge, tactics, and strategies as it faces new challenges in the game and more capable human or automated opponents. For more information see the ALMECOM pages and some of the detailed papers on metacognition in Bolo.

Posted in AI, CS, UMBC Research, research | No Comments »

Adding AI to games

The Guardian has an article, The hard-thought race for intelligent gaming, on efforts to add AI techniques to games to make them more interesting.

“Gaming has a lot in common with everyone’s favorite heiress, at least in the public consciousness: it’s pretty, but dumb. And now that Microsoft, Nintendo and Sony have released their latest games consoles, that statement becomes all the more pertinent - next-gen games look great, but they play like something that could have been made a decade ago. While visual fidelity has advanced exponentially over time, the technology that governs how games play, react and adapt - the artificial intelligence, or AI - remains relatively rudimentary.”

The article talks about Creatures, a series of artificial life simulation games developed in the 90sthat used various kinds of machine learning and Fable 2, an upcoming video game for the Xbox 360.

Posted in AI, General | No Comments »