Decision model training method and device, computer equipment and storage medium

The embodiment of the invention discloses a decision model training method and device, computer equipment and a storage medium, and belongs to the field of artificial intelligence. The method comprises the steps that a first model pool is acquired, the first model pool comprises at least one decision model, and the decision model is used for indicating a fight strategy adopted by a virtual character during wartime; in the nth iteration process, the ith battle state data are input into the nth decision model, an action instruction output by the nth decision model is obtained, and the action instruction is used for instructing the first client to control the first virtual character to execute the action and feeding back the collected (i + 1) th battle state data after the first virtual character executes the action; training the nth decision model based on the battle state data in the battle process to obtain an (n + 1) th decision model; and adding the (n + 1) th decision model to the first model pool. The dec