Poker Neural Nets
Depending on the context, PokerSnowie may either stand for the AI (the 'brain') or the actual software tool that is powered by the brain.
PokerSnowie is the name behind the concept of increasing game proficiency, overall gaming ecosystem health and entertainment value using mathematical modelling and artificial intelligence (neural networks) to develop the strongest, most balanced and ultimately un-exploitable gameplay possible. We want to give everyone the chance to improve their game in an effective yet responsible way for the overall good of the gaming community.
With a standard feedforward neural network the order you feed the network your data is going to have no impact on the predictions. Order may impact training if you're using stochastic or mini-batch gradient descent, but this is only an artifact of the iterative (as opposed to batch) training method. If neural networks are used in a context like NLP, sentences or blocks of text of varying sizes are fed to a Stack Exchange Network Stack Exchange network consists of 176 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.
We've already put our ambition into practice in the form of BackgammonSnowie, which showed fantastic results and a lot of support from novice and professional Backgammon players alike.
With poker increasing in popularity, in addition to the fact that it's a similarly skill-based game with some elements of luck, it was the next logical step in our progression, and resulted in PokerSnowie.
PokerSnowie is a very strong No Limit Hold'em poker player. Its knowledge is based on artificial intelligence neural networks and mathematical models, and its experience is the result of trillions of hands of gameplay against itself over the course of a decade.
PokerSnowie has no expert knowledge built in and its goal is to develop a perfectly balanced and un-exploitable strategy, making it the perfect partner to help you develop a long term winning strategy.
Poker Neural Network
Hey jp, great points. I would have posted the code, but for the life of me I can't find it anywhere. I had the Excel sheet stored in a different folder, which is why I was able to post it.Anyway, I think I was thinking that including the difference from the average value would help the neural network identify pairs. In retrospect, it should have been able to recognize that simply from the card values, no?
Limit holdem had been done a lot and No Limit was my area of expertise, which is why I chose it. I didn't have that much experience with shortstacking, but I had read pretty much everything there was to read on it and it seemed like a good start because of its simplicity. Little did I know that the profits from shortstacking come from a very few carefully timed moves that are close to impossible for a rules-based bot to emulate (more on that in another post). Eventually I decided to build a no limit heads up bot, which is where my success wound up being.
Poker Neural Nets Net
I didn't mention it in the post, but the key was moving away from rules based to a value based system, where the bot calculated the profitability of its options and decided based on that. It was a lot easier to debug, but there were a whole set of challenges to that too, like estimating your opponent's range.