Smart Choices and the Selection Monad

Describing systems in terms of choices and of the resulting costs and rewards offers the promise of freeing algorithm designers and programmers from specifying how those choices should be made; in implementations, the choices can be realized by optimization techniques and, increasingly, by machine learning methods. We study this approach from a programming-language perspective. We define two small languages that support decision-making abstractions: one with choices and rewards, and the other additionally with probabilities. We give both operational and denotational semantics. The operational semantics combine the usual semantics of standard constructs with optimization over a space of possible executions. The denotational semantics, which are compositional and can also be viewed as an implementation by translation to a simpler language, rely on the selection monad. We establish that the two semantics coincide in both cases.