Marcus Hutter

So what you do is you have some experience.

You build models like scientists, you know, of your experience.

Then you hope these models are roughly correct.

And then you use these models for prediction.

That's not the important part.

It is technically important, but at this stage, we can just think about predicting, say, stock market data, weather data, or IQ sequences, one, two, three, four, five, what comes next.

So, of course, our actions

affect what we're doing, but I come back to that in a second.

Okay, if you want to put the actions in now, okay, then let's put in them now.

We don't have to put them now.

Scratch it, dumb question.

Okay, so the simplest form of prediction is that you just have data which you passively observe and you want to predict what happens without interfering.

as I said, weather forecasting, stock market, IQ sequences, or just anything, okay?

And Solomonov's theory of induction based on compression, so you look for the shortest program which describes your data sequence, and then you take this program, run it, it reproduces your data sequence by definition, and then you let it continue running, and then it will produce some predictions.

And you can rigorously prove that for any prediction

prediction task, this is essentially the best possible predictor.

Of course, if there's a prediction task,

or a task which is unpredictable, like, you know, fair coin flips.

Yeah, I cannot predict the next fair coin flip.

What Solomonov does is says, okay, next head is probably 50%.