Reinforcement Learning in Card Game Environments Using Monte Carlo Methods and Artificial Neural Networks

Artificial intelligence has wide range of application areas and games are one of the important ones. There are many applications of artificial intelligence methods in game environments. It is very common for game environments to include intelligent agents. Having intelligent agents makes a game more entertaining and challenging for its players. Reinforcement learning methods can be applied to develop artificial intelligence agents that learn to play a game by themselves without any supervision and can play it at a high level of expertize. Supervised learning methods, on the other hand, can be applied to develop agents that play a game by imitating the supervisor players. The purpose of this study is to develop self-learning agents for a card game, namely Batak, using reinforcement learning combined with supervised learning. Batak is a trick-taking card game popular in Turkey. Results of the study reveal that the developed agents are better at gameplaying and similar at bidding compared to some rule based Batak playing agents.