![]() Our agents were evaluated against several benchmark agents. Furthermore, we adapt heuristics such as halls of fame and co-evolution to be able to handle populations of Poker agents, which can sometimes contain several hundred opponents, instead of a single opponent. In this paper, we present several algorithms for teaching agents how to play No-Limit Texas Hold'em Poker using a hybrid method known as evolving neural networks. Evolutionary methods have been shown to find relatively good results in large state spaces, and neural networks have been shown to be able to find solutions to non-linear search problems. Poker has a much larger game space than classic parlour games such as Chess and Backgammon. The game contains a high degree of stochasticity, hidden information, and opponents that are deliberately trying to misrepresent their current state. Computers have difficulty learning how to play Texas Hold'em Poker.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |