maxpumperla / deep_learning_and_the_game_of_go

Hi! I am reading your book and I think I found an error in Ch 13.

Why do you reset self.root here

deep_learning_and_the_game_of_go/code/dlgo/agent/alphago.py

Line 118 in 50aa0ce

self.root = AlphaGoNode()

before referencing it below?

deep_learning_and_the_game_of_go/code/dlgo/agent/alphago.py

Line 119 in 50aa0ce

if move in self.root.children: # <2>

I don't know what was the intention of it but I believe this would be wrong since that will never be executed.

found out this #42
so closing it

This code is wrong either:

if move in self.root.children: 
    self.root = self.root.children[move]
    self.root.parent = None
else:
    self.root = AlphaGoNode()
return move

since else is never executed and self.root cannot reflect opponent's move so that it eventually makes illegal moves.

To solve this, there are two choices:

reset by self.root = AlphaGoNode() no matter what.
make a new function that when opponent makes a move, reflect it on self.root. e.g.,

def reflect_move(self, move):
    if move in self.root.children: 
        self.root = self.root.children[move]
        self.root.parent = None
    else:
        self.root = AlphaGoNode()

Please let me know if I'm wrong.

Ch 13 agent/alphago.py wrong code?