Last updated
Construction of agents that perceive and act to maximise some objective. Modern AI is dominated by gradient-based learning on differentiable models.
Bayes: $P(h|d) = P(d|h)P(h)/P(d)$
Expected utility: $\mathbb{E}[U] = \sum_a P(a) U(a)$
Solomonoff prior: $M(x) = \sum_{p : U(p)=x*} 2^{-|p|}$
Last updated