![play against a shanky bot play against a shanky bot](https://i.ytimg.com/vi/LxwsifjS8g8/maxresdefault.jpg)
The output was simply a 1 if it had raised and a 0 if it had folded. The difference between the second card’s value and the average The difference between the first card’s value and the averageħ.
![play against a shanky bot play against a shanky bot](https://www.warbotpoker.com/wp-content/uploads/2016/04/Millennium.jpg)
The average value of the two hole cardsĦ. My position at the table where 0 = first to act, 7/9 = 0.778 = Dealerĥ. The numeric value of the second hole card scaled from 0 to 1.ģ. The numeric value of the first hole card scaled from 0 to 1. There were a total of 10,461 hands that met that criteria.
PLAY AGAINST A SHANKY BOT FULL
To test it out, I picked a very specific situation that the shortstacking bot had faced many times in the past: Everyone folds to you preflop at a full ring (8-9 players) table, do you raise or fold? The bot never called in those situations, so I didn’t have to factor that in. I had been testing the it for several weeks when I decided to try out the neural network idea, so I had plenty of data to work with. This made shortstacking the perfect strategy for my fledgling poker bot.Īt that time, the shortstacking bot made its decisions based on some elaborate conditional statements (ex: if you have QQ, KK, or AA and in early position, then raise). You see, when you don’t have a lot of chips to play with, you wind up making a lot of all in decisions preflop and relatively few postflop and most opponents do not adjust correctly to your strategy most opponents play like they’re playing against someone with a normal stack, which is the absolute worst thing you can do against a talented shortstacker. Shortstacking is a nasty little poker strategy that advocates aggressive play with with a relatively small amount chips. Designing a Simple TestĪ little background: My original goal for the poker bot was a full ring shortstacking bot. For a poker bot, this is a pretty appealing idea: you find the hand history of a winning, high stakes player, train the NN, and then set you poker bot loose to win a boat load of money.
PLAY AGAINST A SHANKY BOT HOW TO
“Huh?” you say? Here’s the idea for poker: You give a NN data from previous hands you played (position, card values, hand rank, etc) and the decision you made in those situations (call, raise, fold, bet, check) and the NN will learn how to mimic those decisions. I tested it out and my definitive conclusion is “ Maybe“.Ī neural network (NN) is an AI technique that intelligently maps input values to output values. Their eyes open wide and they excitedly shout to the next stranger they see: “I’ll do it with a neural network!” Seems like such a good idea, right? This is post #11 in an ongoing series of articles about my work as a poker bot developer.Īt one point or another most poker bot developers have an epiphany.