Decision making (DM) can be seen as a purposeful choice of action sequences.
A range of prescriptive theories have been proposed how to make optimal decisions under these conditions.
While the probabilistic description of beliefs is uniquely and deductively driven by rules for joint probabilities, the composition and decomposition of the loss function have no such universally applicable formal machinery.
Fully probabilistic design (of decision strategies or control, FPD) removes the mentioned drawback and expresses also the DM goals of by the "ideal" probability, which assigns high (small) values to desired (undesired) behaviours of the closed DM loop formed by the influenced world part and by the used strategy.
[1][2] FPD has a range of theoretical consequences ,[3] [4] and, importantly, has been successfully used to quite diverse application domains.