This paper proposes an agent-based computational model of the Italian wholesale electricity market. In particular, the aim of the paper is to study how the strategic behavior of the thermal power plants can influence the level of price at a zonal and national level with respect of a typical daily load profile. The model reproduces exactly the market clearing procedure, i.e., day-ahead market (DAM) and the Italian high-voltage transmission network with its zonal subdivision. Furthermore the daily load profile and all installed thermal power plants are realistically considered. Three price cases are studied and compared, i.e., the real situation, a cost based case and a final case where the generation companies learn according to a reinforcement learning algorithm their best strategy. The empirical validation at a national level enables to point out that the model replicate correctly historical data except for some peak-load hours.