Impulsivity is a pathological symptom in several psychiatric disorders, underscoring the need for animal models of impulsive action to develop a brief screening method for novel therapeutic agents of impulsive action. The aims of this study were (i) to evaluate whether the three-choice serial reaction time task (3-CSRTT), a simple version of the five-choice serial reaction time task (5-CSRTT), is appropriate for brief assessment of impulsive-like action and (ii) to examine the effects of fluvoxamine, a selective serotonin reuptake inhibitor, and milnacipran, a serotonin/noradrenaline reuptake inhibitor, on impulsive-like action using the 3-CSRTT. After training in the 3-CSRTT, rats were administered nicotine (0, 0.1, 0.2, and 0.4 mg/kg, salt, subcutaneously), atomoxetine [0, 0.01, 0.1, and, 1.0 mg/kg, intraperitoneally (i.p.)], fluvoxamine (0, 2, 4, and 8 mg/kg, i.p.), or milnacipran (0, 3, and 10 mg/kg, i.p.). The training time for the 3-CSRTT was significantly shorter than that for the 5-CSRTT. Nicotine increased, whereas atomoxetine decreased the number of premature responses, an index of impulsive-like action, which is consistent with earlier studies. Milnacipran, but not fluvoxamine, dose-dependently decreased premature responses. These results indicate that the 3-CSRTT could provide an appropriate and simpler rodent model of impulsive-like action and that milnacipran could have some beneficial effects on impulsivity-related disorders.