A Monte Carlo AIXI Approximation · HackerPapers discussions

A Monte Carlo AIXI Approximation — mentioned by sanxiyn

Wed, 31 Jan 2024 02:39:27 GMT

They have been doing this forever. Here is a paper by some of the same authors: A Monte Carlo AIXI Approximation (2009). https://arxiv.org/abs/0909.0801

Paper and discussion history. A mention is not an endorsement.

A Monte Carlo AIXI Approximation — mentioned by tlb

Fri, 09 Nov 2018 16:16:59 GMT

The human mind isn't exactly Solomonoff, because we often hold theories that are more complicated than necessary. Working towards simpler scientific or mathematical theories takes decades. So it seems like we don't just have SI in the inner loop. People have made plausible attempts to approximate SI with practical amounts of computing, like AIXI (https://arxiv.org/abs/0909.0801).

Paper and discussion history. A mention is not an endorsement.

A Monte Carlo AIXI Approximation — mentioned by orangecat

Tue, 09 Mar 2010 21:21:48 GMT

If you apply Ockham's razor in the form "prefer hypotheses with lower Kolmogorov complexity" together with Bayes' theorem, you get something that in a certain (rather artificial) sense is as effective a problem solver as anything mechanized can be. Unfortunately it's unimplementable in practice, because ... Coming across AIXI was what got me interested in algorithmic information theory. It is indeed useless in it's "pure" form, but there's a variation using Monte Carlo search that apparently does pretty well: http://arxiv.org/abs/0909.0801 (This is controversial, but it's my opinion and that…

Paper and discussion history. A mention is not an endorsement.