On Automating the Doctrine of Double Effect

Abstract

The doctrine of double effect (DDE) is a longstudied ethical principle that governs when actions that have both positive and negative effects are to be allowed. The goal in this paper is to automate DDE. We briefly present DDE, and use a firstorder modal logic, the deontic cognitive event calculus, as our framework to formalize the doctrine. We present formalizations of increasingly stronger versions of the principle, including what is known as the doctrine of triple effect. We then use our framework to successfully simulate scenarios that have been used to test for the presence of the principle in human subjects. Our framework can be used in two different modes: One can use it to build DDE-compliant autonomous systems from scratch; or one can use it to verify that a given AI system is DDE-compliant, by applying a DDE layer on an existing system or model. For the latter mode, the underlying AI system can be built using any architecture (planners, deep neural networks, bayesian networks, knowledge-representation systems, or a hybrid); as long as the system exposes a few parameters in its model, such verification is possible. The role of the DDE layer here is akin to a (dynamic or static) software verifier that examines existing software modules. Finally, we end by sketching initial work on how one can apply our DDE layer to the STRIPS-style planning model, and to a modified POMDP model. This is preliminary work to illustrate the feasibility of the second mode, and we hope that our initial sketches can be useful for other researchers in incorporating DDE in their own frameworks.

On Quantified Modal Theorem Proving for Modeling Ethics

“…According to DDE, an action α in such a situation is permissible iff "(1) it is morally neutral; (2) the net good consequences outweigh the bad consequences by a large amount; and (3) some of the good consequences are intended, while none of the bad consequences are. [11]"…”

“…A formalization of DDE is presented in [11]. While DDE has some empirical support [9], it cannot account for instances of self-sacrifice.…”

“…For example, a quantified modal logic, the deontic cognitive event calculus (DC EC ), has been used recently to model various versions of the Doctrine of Double Effect, akrasia, and virtue ethics [14,12,15,13,7]. These ethical principles and theories have a unique set of characteristics when compared with other domains, e.g.…”

Learning Ex Nihilo

“…Figure 2 is a proof in a cognitive calculus, viz. the one described in (Govindarajulu & Bringsjord 2017a), of Robert learning the following propositions: "Robert believes that his host is wealthy", "The host believes Robert believes that his host is wealthy", and "Robert believes that his host believes Robert believes that his host is wealthy." 13 The figures illustrate first-order and cognitive-calculus reasoners (shown as FOL and CC , resp.)…”

“…Roughly, cognitive calculi include inferential components of intensional higher-order multi-operator quantified logics, in which expressivity far outstrips off-the-shelf modal logics and possible-worlds semantics, and a number of such calculi have been introduced as bases for AI that is unrelated to learning; e.g. see (Govindarajulu & Bringsjord 2017a). The very first cognitive calculus, replete with a corresponding implementation in ML, was introduced in (Arkoudas & Bringsjord 2009).…”