search

AppliedDataSciencePartners / DeepReinforcementLearning

A replica of the AlphaZero methodology for deep reinforcement learning in Python
GNU General Public License v3.0
2.02k stars 758 forks source link

Value can never 1 #35

Open Satokaheni opened 5 years ago

Satokaheni commented 5 years ago

Line 116 of funcs.py I'm not sure value can ever be 1 based on how you've defined it in game.py. Based on game.py function _getValue it can only ever be -1 or 0.

KUEE1080 commented 4 years ago

I also think value can never be 1. Has anyone fixed this issue?

hccho2 commented 4 years ago

If the game is over on your turn, you lost the game because the game was over by the action immediately before it.

So value is always -1.

It is not a bug, but the codes for value=1 are redundant.