PhilGoetz comments on 30th Soar workshop - Less Wrong

18 Post author: Johnicholas 23 May 2010 01:33PM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (18)

You are viewing a single comment's thread.

Comment author: PhilGoetz 24 May 2010 09:54:16PM *  2 points [-]

he's getting Rete to run as an emergent consequence of the sum-product algorithm.

Say what? How does that work?

I was a bit disappointed, since (as far as I can tell) this work simply used Soar as an exotic programming language.

Pretty much all Soar work uses Soar as an exotic programming language. It's a production system. When I studied it, which admittedly was 18 years ago, it had no learning component beyond a mysterious, programmer-dependent "chunking". I would call it a cognitive infrastructure, that you can use to build a cognitive architecture.

Its claim to being a cognitive architecture relied (at least originally) largely on being able to model human performance time on different tasks. But any programming language will be able to do that, if the task naturally has some particular input-dependent runtime, and the task is described properly.

Soar has the problem that it's funded by the military, who want to use it in simulations eg JSAF; but they want untrained military personnel to be able to build things with it. They don't want a smarter AI as much as they want an easier-to-use AI.

Comment author: Johnicholas 25 May 2010 02:18:45AM 0 points [-]

I only saw the 15-minute version, and I didn't understand it, but Rosenbloom's papers, including an unpublished one about the "Bayesian Decision Cycle" are online: http://cs.usc.edu/~rosenblo/pubs.html