Dear Resident Theists

[Angrboda]

Here is a snippet from the article.

---

A player’s move was determined by evaluating the presumed quality of the resulting future positions. The evaluation function was structured as an artificial neural network comprising an input layer, three internal processing (hidden) layers, and an output node (Figure 2). The first internal processing layer was designed to indicate the spatial characteristics of the checkerboard without indicating explicitly how such knowledge might be applied. The remaining internal and output neurons operated based on the dot product of the evolvable weighted connections between nodes and the activation strength that was emitted by each preceding node. Each node used a hyperbolic tangent (tanh, bounded by ±1) with an evolvable bias term. In addition, the sum of all entries in the input vector was supplied directly to the output node, constituting a measure of the relative piece differential.

---

Notice the words "structured" and "designed". The programmers set value to moves that produced positive results so that the programs evolution function could examine the possible moves and learn from the past what has provided the most favorable outcome.

I think you're misinterpreting things, but we could argue this until dooms day with no result. So I'll leave you with the last word.