The most important property of the Iranian Electricity Market is the pay as bid method for the winning power plants. However, in many developed countries' electricity markets, uniform payment method is used. In this paper, we compare the uniform payment method and pay as bid regarding price and cost price of electricity in the Iranian electricity market using a Q-learning model in three periods of low, normal and peak loads. Due to insufficient and in many cases, inaccessible data, this study is mainly concentrated on power plants located in Khorasan Province. According to the results, the price of electricity in the pay as bid method is lower than the uniform payment method. However, the cost of electricity in a uniform layment is less than the pay as bid method. In other words, in a uniform payment, power plants with higher efficiency win the bids resulting into lower fuel consumption and less greenhouse gase emissions.