Re:Bill Joy: Why the future doesn't need us (2004)
by NY_USA_Hacker on Sunday April 24, 2011 @02:18PM
(#2479322)
So AIXI is just old stochastic optimal control (decision theory, controlled Markov processes, R. Bellman's work, etc.) plus a way from Solomonoff to make extrapolations. Okay.
For practice, there have been related ideas from D. Bertsekas and R. Rockafellar.
For actual computing, the problem remains the curse of dimensionality: This curse is so bad that, for a brute force approach, which is what AIXI is, or really nearly anything general in stochastic optimal control on big problems, a few more decades of Moore's law still won't scratch the surface.
For practice, there have been related ideas from D. Bertsekas and R. Rockafellar.
For actual computing, the problem remains the curse of dimensionality: This curse is so bad that, for a brute force approach, which is what AIXI is, or really nearly anything general in stochastic optimal control on big problems, a few more decades of Moore's law still won't scratch the surface.