In　this　paper,　the　decentralised　tracking　control　(DTC)　problem　is　investigated　for　a　class　of　continuous-time　large-scale　systems　with　external　disturbance　by　utilising　adaptive　dynamic　programming　(ADP).　Firstly,　the　DTC　problem　is　solved　by　designing　corresponding　optimal　controllers　of　the　isolated　subsystems,　which　are　formulated　with　N　augmented　subsystems　consisting　of　the　tracking　error　and　the　reference　trajectory.　Then,　considering　the　external　disturbance,　we　can　effectively　construct　the　DTC　scheme　by　means　of　adding　suitable　feedback　gains　to　the　optimal　control　strategies　associated　with　each　augmented　tracking　isolated　subsystems　(ATISs).　Due　to　the　approximate　nature,　a　series　of　critic　neural　networks　are　constructed　to　solve　the　Hamilton-Jacobi-Isaacs　equation,　so　as　to　derive　the　estimation　of　the　Nash　equilibrium　solution　containing　the　optimal　control　strategy　and　the　worst　disturbance　law.　Herein,　a　modified　weight　updating　criterion　is　developed　by　employing　a　stabilising　term.　Consequently,　we　remove　the　requirement　of　initial　admissible　control　in　the　proposed　algorithm.　After　that,　stability　analysis　of　the　ATIS　is　performed　through　the　Lyapunov　theory,　in　the　sense　that　tracking　states　and　weight　approximation　errors　are　uniformly　ultimately　bounded.　Finally,　an　experimental　simulation　is　demonstrated　to　ensure　the　validity　of　the　proposed　DTC　scheme.