Learning a commonsense moral theory

  title={Learning a commonsense moral theory},
  author={Max Kleiman-Weiner and Rebecca Saxe and Joshua B. Tenenbaum},

A Computational Model of Commonsense Moral Decision Making

A computational model for building moral autonomous vehicles by learning and generalizing from human moral judgments is introduced and it is shown that an individual's moral values -- as well as a group's shared values -- can be inferred from sparse and noisy data.

Moral learning: Psychological and philosophical perspectives

Is morality a gadget? Nature, nurture and culture in moral development

It is argued that to achieve these objectives research on moral learning needs to overcome nativist bias, and distinguish two kinds of social learning: learning from and learning about.

Moral learning : Current and future directions

The past 15 years occasioned an extraordinary blossoming of research into the cognitive and affective mechanisms that support moral judgment and behavior. This growth in our understanding of moral

Modeling Morality in 3‐D: Decision‐Making, Judgment, and Inference

This work describes the advantages of investigating the three dimensions of moral cognition within a single computational framework and shows how this framework can provide novel insights into the mechanisms of moral decision‐making, judgment, and inference.

Adopted Utility Calculus: Origins of a Concept of Social Affiliation

  • Lindsey J. Powell
  • Psychology
    Perspectives on psychological science : a journal of the Association for Psychological Science
  • 2022
To successfully navigate their social world, humans need to understand and map enduring relationships between people: Humans need a concept of social affiliation. Here I propose that the initial

Learning tractable probabilistic models for moral responsibility and blame

This work proposes and implements a hybrid (between data-driven and rule-based methods) learning framework for inducing models of moral scenarios automatically from data and reasoning tractably from them and reports on experiments that compare the system with human judgement in three illustrative domains.

Learning from moral inconsistency




Moral learning as intuitive theory revision

Action, Outcome, and Value: A Dual-System Framework for Morality

Dual-system approaches to psychology explain the fundamental properties of human judgment, decision making, and behavior across diverse domains. Yet, the appropriate characterization of each system

Mechanisms of social cognition.

It is suggested that meta-cognitive processes can also exert control over automatic behavior, for instance, when short-term gains oppose long-term aims or when selfish and prosocial interests collide and underlie the ability to explicitly share experiences with other agents.

Learning a theory of causality.

It is suggested that the most efficient route to causal knowledge may be to build in not an abstract notion of causality but a powerful inductive learning mechanism and a variety of perceptual supports, which have implications for cognitive development.

Rational Learners and Moral Rules

People draw subtle distinctions in the normative domain. But it remains unclear exactly what gives rise to such distinctions. On one prominent approach, emotion systems trigger non-utilitarian

The mentalistic basis of core social cognition: experiments in preverbal infants and a computational model.

Evidence from 10-month-olds is presented, motivated and supported by a Bayesian computational model, for mentalistic social evaluation in the first year of life.

Universal moral grammar: theory, evidence and the future