# Acting for the Right Reasons: Creating Reason-Sensitive Artificial Moral Agents

arXiv: https://arxiv.org/abs/2409.15014 · HTML: https://mlsanity.com/paper/2409.15014/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 4 of 4)

- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [A Practical Guide to Multi-Objective Reinforcement Learning and Planning](https://mlsanity.com/paper/2103.09568/) (2021)
- [Towards a Framework Combining Machine Ethics and Machine Explainability](https://mlsanity.com/paper/1901.00590/) (2019)
- [Reinforcement Learning and Machine ethics:a systematic review](https://mlsanity.com/paper/2407.02425/) (2024)

## Built on by (most cited first, 1 of 1)

- [Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment](https://mlsanity.com/paper/2601.10520/) (2026)

## Abstract (arXiv)

We propose an extension of the reinforcement learning architecture that enables moral decision-making of reinforcement learning agents based on normative reasons. Central to this approach is a reason-based shield generator yielding a moral shield that binds the agent to actions that conform with recognized normative reasons so that our overall architecture restricts the agent to actions that are (internally) morally justified. In addition, we describe an algorithm that allows to iteratively improve the reason-based shield generator through case-based feedback from a moral judge.