Vehicle control method based on reinforcement learning control strategy in hybrid fleet

The invention provides a vehicle control method based on a reinforcement learning control strategy in a hybrid fleet, and the method comprises the steps: initializing a hybrid fleet, and building a fixed reference system and an inertial reference system; establishing a model of a mixed vehicle longitudinal queue in the inertial reference system; constructing a Lagrange quadratic queue car-following cost function, and obtaining an expression of a Q value function; training information obtained by the influence of surrounding vehicles on own vehicles by using a deep Q learning network; trainingparameters by using a DDPG algorithm, and if the Q value function process and the control input process realize convergence at the same time, completing the solution of the current optimal control strategy; inputting the optimal control strategy into the model of the longitudinal queue of the hybrid vehicle, and updating the state of the hybrid vehicle by the hybrid vehicle queue; and repeating the steps to finally comple