Communication resource allocation method and device and nonvolatile storage medium

The invention discloses a communication resource allocation method and device and a nonvolatile storage medium. Relates to the technical field of communication, and the method comprises the steps: constructing an optimization target which is used for indicating that the outage probability of a communication network is minimum; determining a device set corresponding to the cell base station and a resource block set corresponding to the communication network; based on the resource block set, utility functions corresponding to the devices included in the device set are determined, and the utility functions are used for evaluating preference degrees of the corresponding devices to different resource blocks; and reinforcement learning is carried out based on the optimization target and the utility functions corresponding to the devices included in the device set to obtain a communication resource allocation result, and the communication resource allocation result is used for indicating resource block allocation re