Stanford AI Class

During the past few weeks I've been following the video lectures that Sebastian Thrun and Peter Norvig post every week, and that constitute their "Introduction to Artificial Intelligence" course.

I have to say that I love the course. Even if, as an AI researcher, I should know everything that they explain, it's nice to hear it again properly summarized and explained. What is more interesting about this course is that, given it's crazy amount of students (I've heard the count is about 160000!), it's generating lots of reactions among AI researchers. Some people love it, some people hate it. Here's my take on it.

I agree with many that the course is extremely biased (specially the machine learning part), and that only those techniques coming from probability and statistics are covered in the course. For example, the supervised learning module basically covers Bayesian learning, linear regression and nearest neighbor (and this last one is a nice addition!). This leaves out all the "search-based" machine learning methods (based on the idea of searching in a hypothesis space) like: version spaces or decision trees. This is an "introduction to AI" class, and I understand that they leave out the more fashionable topics like kernel methods. But I think that the search-based approach to machine learning deserves a module in this course. Whole fields (like inductive logic programming) come from this tradition of machine learning.

The same happens with the planning module of the course. Traditional introductory courses to AI use STRIPS planning to introduce the students to the idea of planning, and only tangentially touch on the problem of planning under uncertainty. However, this course does the opposite. Which is kind of weird. But here I don't have such a strong opinion as with the machine learning module.

Given the large number of students, and the strong bias of the course. Several AI researchers are actually angry at the course, since it's shaping the mind of a whole generation of potential AI researchers.

That said, I still think the course is awesome, and I follow it every week.

And I say this: all of those (and I include myself) who disagree with the way Sebastian and Peter teach their course should, instead of complain, just try to follow their lead and create an online course that represents their view of AI. Maybe we could even create a youtube channel for "missing lectures from the Stanford intro to AI course" :)

LEGO tank with arm

After a bunch of conference deadlines all packed together I decided to take a break and have some fun building LEGO. This time I decided to create an arm. Not very pretty, but I'm kind of proud of the claw. If you are into LEGO technic creationg, check this out:

IEEE-CIG 2010

I recently attended the IEEE-CIG 2010 conference, which stands for the "Computational Intelligence in Games" conference, and I've to say, it was a very interesting experience. I've regularly attended AIIDE (the other game AI conference), but I had never been in CIG. I had the impression that the CIG environment was much more focused on games than in AI, and that made this conference really interesting from an AI researcher's point of view for the following reasons:

1) AI conferences are typically full with researchers (like me) that have a technique they believe in (case-based reasoning, support-vector machines,... you name it) and that are looking for problems they can solve with their technique. Typical "hammer looking for nail". In GIC it was the opposite. It was full of people explaining real problems they face in the creation of video games, and for which they were looking for solutions.
2) On top of that, given that a large proportion of the crowd were more game experts than AI experts, the range of AI techniques exhibited in CIG was quite narrow (as I will detail later). So, I think there are lots of opportunities for AI researchers looking for nails there.

Most of the papers presented some particular AI technique applied to some particular game. I did a rundown of all the 62 papers accepted and this is the histogram of AI techniques being used (not all papers were about AI, so the following numbers do not add up to 62):

- Machine Learning: 11 papers (3 on neural nets, 2 in reinforcement learning, rest on different techniques)
- Search: 7 papers (6 on game tree search)
- Planning: 1 paper
- Optimization: 18 papers (17 on genetic algorithms)
- Statistical: 3
- Game Theory: 2
- Logic: 2
- Scripting: 2
- Cognitive Approaches: 5 (2 on CBR/Episodic memory)
- Drama Management: 1
- Game Specific AI: 5

One quick observation is that there is a huge bias towards certain kind of approaches. For instance, there were 17 papers out of 62 talking about genetic algorithms. And out of all of the papers using some machine learning technique, the only 2 techniques to be used more than once were neural networks and reinforcement learning.

For instance, in one of the competitions held during the conference, the problem was to make an AI which would control a car, and be as fast as possible. The most successful approaches would first optimize a "race-line" using genetic algorithms, and then just have a hard-coded controller which would stick to that line when possible. The problem they faced is that driving a car is not just sticking to the race line: there are other cars in the game which have to be overtaken, etc. Thus, there are several behaviors that need to be modeled: sticking to the race line and overtaking. The AI community has solutions for these kind of problems where there are multiple competing behaviors, such as the subsumption architecture, or the more modern multi-agent bidding coordination mechanisms.

My conclusion is that we, as AI researchers, have a lot to gain by paying attention to places like CIG. On the one hand, we have the chance of contributing to the computer games community by bringing new techniques to the table, and on the other hand, the computer games community have a chance of contributing to the AI community by offering us challenging problems with which to push the limits of current AI techniques.

If anyone is interested, here's a quick list of the competitions that called my attention in CIG:

- Simulated Car Racing Championship: make an AI which races a car through a track with opponents as fast as possible. The problems involve both optimizing the trajectory, real-time control and handling unpredictable events (opponents). URL: http://cig.dei.polimi.it/

- Ms. Pac-Man Competition: create an AI agent which can play Ms. Pac-Man, problems: real-time decision making, non-determinism. URL: http://dces.essex.ac.uk/staff/sml/pacman/PacManContest.html

- Mario AI Championship: create an AI that can play Mario. In addition to the reactive control needed in Ms. Pac-Man, here you need high level planning, since there are levels which require some amount of puzzle-solving ability (e.g. you can only pass by first breaking some stones, and then jumping to a particular position, etc.). URL: http://www.marioai.org/

- The 2K BotPrize: a Turing test for first-person shooter bots, and with a cash prize! URL: http://botprize.org/

- StarCraft RTS AI Competition: if you think Chess is hard. Starcraft has a way bigger action and state space, it is real-time, and there is imperfect information. Good luck trying to create an AI for this! :) URL: http://ls11-www.cs.tu-dortmund.de/rts-competition/starcraft-cig2010

So, what's what I'd like to see next year at CIG? a more varied histogram of AI techniques, and a more varied set of entries to the competitions. I think this would provide a more interesting discussion and also help better understand which techniques are more suitable for which kind of game problems.

SCI/FI Ideas might sometimes not be that random...

Recently some Taiwanese researcher called Wun-Yi Shu published a new model of the universe which does not require a Big Bang. The funny thing is that in a SCI/FI short story I wrote a long time ago I made up an almost identical model.

As explained in this blog "Shu's idea is that time and space are not independent entities but can be converted back and forth between each other. In his formulation of the geometry of spacetime, the speed of light is simply the conversion factor between the two." Well, that's exactly what my character Howard A. Leonard writes in a letter at the beginning of my story "Tropezar con la misma piedra".

I find it quite funny that sometimes random ideas that are made up just to write a SCI/FI story can turn out to be not that random and make some sense after all :)

LEGO linear actuators

I've been recently playing around with the "new" LEGO linear actuators. They are pretty neat and mechanics can get greatly simplified thanks to them. Sometimes it removes a little bit the challenge, but it also increases the creative possibilities.

I created a simple 4-legged walker using 4 linear actuators to test their strength and speed, and I've to say I've been surprised at the quality of those actuators.  Here's a picture of the linear actuator in my robot:

And you can see more pictures and videos of it here

LEGO robots

Recently I decided that it was about to start building LEGO robots again. LEGO has been one of my favorite toys since I was very very young. If LEGO Mindstorms existed when I was a kid, I'd have been the happiest kid in this planet! (not that I wasn't, but anyway ;)). I recently built some LEGO 4 legged walkers and had a lot of fun doing so. I thought I would put them online to see if anyone had any feedback :)

Here's one of them:

Check them out here: http://sites.google.com/site/santiagoontanonvillar/Home/lego-projects

SSH + Screen

This one is not about AI, but about something extremely useful I learned today. Have you ever been running an experiment in a server through SSH and all of asudden the connecton drops? damn! you lose the experiment... try this:

1) ssh to your server

2) screen

3) launch your experiment

4) "Ctrl-a" "d"

now you can quit your ssh and the experiment keeps running in the server. Whenever you want to check how is it going, go and:

5) screen -ls

6) screen -r

boom! you are back in your experiment! Amazingly easy, and amazingly useful. Check the site from where I got the info, here: http://www.rackaid.com/resources/linux-tutorials/general-tutorials/using-screen/