遗传编程或称基因编程，简称GP，是一种从生物演化过程得到灵感的自动化生成和选择计算机进程来完成用户定义的任务的技术。从理论上讲，人类用遗传编程只需要告诉计算机“需要完成什幺”，而不用告诉它“如何去完成”，最终可能实现真正意义上的人工智能：自动化的发明机器。

遗传编程是一种特殊的利用进化算法的机器学习技术，它开始于一群由随机生成的千百万个计算机进程组成的“人群”，然后根据一个进程完成给定的任务的能力来确定某个进程的适合度，应用达尔文的自然选择（适者生存）确定胜出的进程，计算机进程间也模拟两性组合，变异，基因复制，基因删除等代代进化，直到达到预先确定的某个中止条件为止。

In artificial intelligence, genetic programming (GP) is a technique whereby computer programs are encoded as a set of genes that are then modified (evolved) using an evolutionary algorithm (often a genetic algorithm). The result is a computer program able to perform well in a predefined task. Often confused to be a kind of genetic algorithm, GP can indeed be seen as an application of genetic algorithms to problems where each individual is a computer program. The methods used to encode a computer program in an artificial chromosome and to evaluate its fitness with respect to the predefined task are central in the GP technique and still the subject of active research.