#### NewAmerica

##### Senior Member

Mandarin

Is "|" in "P r(a|s) " read as

Thanks in advance

*************************

Instead of a handcrafted evaluation function and move ordering heuristics, AlphaZero utilises a deep neural network (p, v) = fθ(s) with parameters θ. This neural network takes the board position s as an input and outputs a vector of move probabilities p

-arXiv

Source

Source (PDF version)

*vertical line*?Thanks in advance

*************************

Instead of a handcrafted evaluation function and move ordering heuristics, AlphaZero utilises a deep neural network (p, v) = fθ(s) with parameters θ. This neural network takes the board position s as an input and outputs a vector of move probabilities p

**with components pa = Pr(a|s)**for each action a, and a scalar value v estimating the expected outcome z from position s, v ≈ E[z|s].-arXiv

Source

Source (PDF version)

Last edited: