January 7, 2010
I just spotted another .NET implementation of Rete – NRuler. The site shows only 10 downloads, but it seems to have been live less than a month so far. Any of the 10 downloaders care to share their impressions? How does it compare with NxBRE or SRE?
(As an aside, I spotted NRuler because it is linked in the “See also” section of the Wikipedia article on Rete. At best, the link to NRuler should be an “External link” rather than a “See also” – and probably not even that. As an industry, we need to stop spamming this article with promotional product-specific links. Yes, I know that NRuler isn’t a commercial product, but I don’t see any reason for it to be linked there over any other piece of software.)
No Comments » | 
.NET, AI, rules | Tagged: .NET, AI, Microsoft, NRuler, NxBRE, rete, rule engine, rules, Simple Rule Engine, SRE | 
Permalink
Posted by Karl W. Reinsch
January 6, 2010
I recently stumbled across another rule engine for .NET that I hadn’t seen before: Simple Rule Engine (SRE).
Looks dormant, or possibly dead altogether. If any readers have tried it out, I welcome comments about your experiences with it.
No Comments » | .NET, AI, rules | Tagged: .NET, AI, Microsoft, rete, rule engine, rules, Simple Rule Engine, SRE | Permalink
Posted by Karl W. Reinsch
November 19, 2009
The results of the Mario Bros. AI competition have been made available. (Not really surprising that the top three entries used A*.)
Robin Baumgarten has won, and has made his source code available. AIGameDev.com also has an interview with Robin.
No Comments » | AI, games, video games | Tagged: A*, AI, games, machine learning, Mario, Nintendo, video games | Permalink
Posted by Karl W. Reinsch
August 6, 2009
Julian Togelius and Sergey Karakovskiy have organized a competition to create an agent (or AI) that plays the video game Super Mario Bros. – or, more accurately, Infinite Mario Bros. a tribute game featuring random level generation.
The advantage of using Infinite Mario Bros. is the random level generation – which can let the agent learn more generalized playing tactics rather than tactics that are tailored to a static set of levels as in Ms. Pac-Man or Pitfall.
I look forward to seeing the results of the competition, and hope to see source code published as well.
No Comments » | AI, games, video games | Tagged: AI, games, machine learning, Mario, Ms. Pac-Man, Nintendo, Pitfall, video games | Permalink
Posted by Karl W. Reinsch
June 29, 2009
The Netflix Prize has entered the 30-day notification period as a team has announced that they have achieved a 10.05% improvement over the original Cinematch algorithm.
Some further background on the contest can be found in a nice writeup in Wired from last year.
No Comments » | AI, datamining | Tagged: AI, algorithms, datamining, machine learning, Netflix | Permalink
Posted by Karl W. Reinsch
June 29, 2009
From Rutgers university comes a learning algorithm that they have applied to playing the Atari 2600 game “Pitfall!”.
An example video is on YouTube.
One of the research papers is apparently here (although the site isn’t being very responsive at the moment).
I’ll get around to posting on machine learning for Pac-Man/Ms. Pac-Man at some point as well.
(Spotted on Kotaku and GameSetWatch.)
No Comments » | AI, games, video games | Tagged: AI, Atari 2600, games, machine learning, Pitfall, video games | Permalink
Posted by Karl W. Reinsch
May 3, 2009
No Comments » | AI, Microsoft, rules | Tagged: AI, BizTalk, BizTalk BRE, expert systems, Microsoft, Microsoft BRE, rete, rules, Ship-It | Permalink
Posted by Karl W. Reinsch
March 25, 2009
I’ve been watching the multi-core video card space and looking at efforts to offload AI onto that hardware. In particular, I’m curious to see the shakeout of the various APIs. One candidate usage is, of course, video games.
Read the rest of this entry »
No Comments » | AI, games, video games | Tagged: AI, pathfinding, video games | Permalink
Posted by Karl W. Reinsch
February 16, 2009
And what do we have here? It seems that Nvidia and AMD are already on top of the idea of offloading AI onto GPUs.
Read the rest of this entry »
6 Comments | AI, video games | Tagged: AI, AMD, Cuda, GPGPU, multicore, NVidia, parallelism, video games | Permalink
Posted by Karl W. Reinsch
December 7, 2008
Gary Riley’s comment here on November 6 alerted me to a book that I didn’t have: The Engineering of Knowledge-Based Systems: Theory and Practice by Avelino J. Gonzalez and Douglas D. Dankel. So, I went to Amazon to track it down. The book is out of print, so I purchased a used copy.
When my copy arrived a little while ago, I quickly noticed that the owner’s name written inside the cover was that of John Durkin, the noted author of Expert Systems: Design and Development. I spotted it quickly since at a previous employer this book (along with Gary Riley’s book) was used in both internal and external training.
Read the rest of this entry »
1 Comment | AI, books, rules | Tagged: AI, books, expert systems, rules | Permalink
Posted by Karl W. Reinsch
