agent.py 文件源码

def __act_manual(self, state_meas):
        if len(self.__measure_for_manual):
            # [AMMO2, AMMO3, AMMO4, AMMO5, AMMO6, AMMO7, WEAPON2,
            # WEAPON3 WEAPON4 WEAPON5 WEAPON6 WEAPON7 SELECTED_WEAPON]
            assert len(self.__measure_for_manual) == 13
            # [SELECT_WEAPON2 SELECT_WEAPON3 SELECT_WEAPON4 SELECT_WEAPON5 SELECT_WEAPON6 SELECT_WEAPON7]
            curr_action = np.zeros((state_meas.shape[0], self.__num_manual_controls), dtype=np.int)
            for ns in range(state_meas.shape[0]):
                curr_ammo = state_meas[ns, self.__measure_for_manual[:6]]
                curr_weapons = state_meas[ns, self.__measure_for_manual[6:12]]
                if self.verbose:
                    print 'current ammo:', curr_ammo
                    print 'current weapons:', curr_weapons
                available_weapons = np.logical_and(curr_ammo >= np.array([1, 2, 1, 1, 1, 40]), curr_weapons)
                if any(available_weapons):
                    best_weapon = np.nonzero(available_weapons)[0][-1]
                    if not state_meas[ns, self.__measure_for_manual[12]] == best_weapon + 2:
                        curr_action[ns, best_weapon] = 1
            return curr_action
        else:
            return []