For the path tracking control problem of autonomous vehicles with four-wheel steering and four-wheel drive (4WS-4WID), traditional model-driven methods usually rely on a preset vehicle-road model, which makes the controller difficult to adapt to the parameter uncertainties caused by vehicle characteristics or environmental factors. At the same time, when driving in complex conditions, it faces the target conflict of tracking accuracy and stability. To overcome this challenge, we propose a data-driven approach that combines game output regulation and adaptive dynamic programming (ADP). Firstly, a 2-DOF vehicle model and a path following error model are constructed to integrate vehicle-road dynamics. Then, the output adjustment mechanism was further used to deal with the road curvature disturbance, and the progressive tracking was realized under the stability of the closed-loop system. Then, a dynamic game framework of active front wheel steering (AFS), active rear wheel steering (ARS) and drive system (4WID) was established to solve the coordination between path tracking and stability. Finally, the ADP algorithm iteratively optimized the steering and direct yaw moment control strategy through real-time system state and input information without accurate information of the vehicle model. Finally, it was verified by Matlab/Simulink and Carsim simulation software.