A terminal value is an ultimate goal, an end-in-itself. In an AI with a utility or reward function, the terminal value is the maximization of that function.
In Eliezer Yudkowsky's earlier writings, the non-standard term "supergoal" is used instead.
Terminal values vs. instrumental
Terminal values stand in contrast to instrumental values, which are means-to-an-end, mere tools in achieving terminal values. For example, if a given university student does not enjoy studying but is doing so merely as a professional qualification, his terminal value is getting a job, while getting good grades is an instrument to that end.
Some values may be called "terminal" merely in relation to an instrumental goal, yet themselves serve instrumentally towards a higher goal. In the previous example, the student may want the job to gain social status and money; if he could get prestige and money without working he would; and in this case the job is instrumental to these other values. However, in considering future AI, the phrase "terminal value" is generally used only for the top level of the goal hierarchy: the true ultimate goals of a system, those which do not serve any higher value.
Human terminal values
Humans system of terminal values is quite complex. The values were forged by evolution in the ancestral environment to maximize inclusive genetic fitness. These values include survival life, health, friendship, social status, love of various kinds, joy, aesthetic pleasure, curiosity, and much more. Humans do not have inclusive genetic fitness as a goal. Rather, these instrumental values (from the perspective of inclusive genetic fitness) have become humans' terminal values (an example of subgoal stomp).
- The paperclip maximizer and AIXI an examples
- Benevolence as an instrumental and as a terminal value
- Shifts in human terminal values
- Subgoal stomp ("goal displacement") in both senses
- A person wants to get rich to better enjoy life, and because of a total focus on money, becomes a workaholic focused on money for its own sake.
- Humans as adaptation executors
Eliezer Yudkowsky, Terminal Values and Instrumental Values