News for hackers. Stuff that matters.
Re:The Steely, Headless King of Texas Hold ’Em by thisisnotatest on Thursday September 05, 2013 @02:44PM (#6336018)
I don't see what you get from asking people what they think they'd do in certain situations, when you could instead use the actual outcome of the hand as your training labels.
Re:The Steely, Headless King of Texas Hold ’Em by ianstallings on Thursday September 05, 2013 @03:40PM (#6336428)
Validation mainly. Because I worry that the hand histories might not be enough and they may be tainted with more examples of bad play than good. I would like to qualify good play with some human validation.

But I think it's worth looking at to only use hand histories and if possible only validate when something unexpected results. Maybe then I could use the human input to validate the computer's decision. I'm still hashing that out.