This letter investigates an intelligent reflecting surfaces (IRS)-enhanced network from spectral efficiency enhancement point of view for downlink multi-user (MU) multi-input-single-output systems (MISO). In contrast to previous works which mainly focused on alternative optimization methods, we investigate the non-convex joint optimization problem of the active transmit beamforming matrix at the base station together with the passive phase shift matrix at the IRS by utilizing two deep reinforcement learning frameworks, i. e., deep deterministic policy gradient (DDPG) and twin delayed DDPG (TD3). Simulation results reveal that the neural networks in the latter scheme perform generally more satisfactorily in various situations.