Reinforcement Learning Guided by Provable Normative Compliance

• URL: http://arxiv.org/abs/2203.16275v1
• Date: Wed, 30 Mar 2022 13:10:55 GMT
• Title: Reinforcement Learning Guided by Provable Normative Compliance
• Authors: Emery Neufeld
• Abstract summary: Reinforcement learning (RL) has shown promise as a tool for engineering safe, ethical, or legal behaviour in autonomous agents. We use multi-objective RL (MORL) to balance the ethical objective of avoiding violations with a non-ethical objective. We show that our approach works for a multiplicity of MORL techniques, and show that it is effective regardless of the magnitude of the punishment we assign.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) has shown promise as a tool for engineering safe, ethical, or legal behaviour in autonomous agents. Its use typically relies on assigning punishments to state-action pairs that constitute unsafe or unethical choices. Despite this assignment being a crucial step in this approach, however, there has been limited discussion on generalizing the process of selecting punishments and deciding where to apply them. In this paper, we adopt an approach that leverages an existing framework -- the normative supervisor of (Neufeld et al., 2021) -- during training. This normative supervisor is used to dynamically translate states and the applicable normative system into defeasible deontic logic theories, feed these theories to a theorem prover, and use the conclusions derived to decide whether or not to assign a punishment to the agent. We use multi-objective RL (MORL) to balance the ethical objective of avoiding violations with a non-ethical objective; we will demonstrate that our approach works for a multiplicity of MORL techniques, and show that it is effective regardless of the magnitude of the punishment we assign.

Related papers

• Using AI Alignment Theory to understand the potential pitfalls of regulatory frameworks [55.2480439325792]
  This paper critically examines the European Union's Artificial Intelligence Act (EU AI Act) Uses insights from Alignment Theory (AT) research, which focuses on the potential pitfalls of technical alignment in Artificial Intelligence. As we apply these concepts to the EU AI Act, we uncover potential vulnerabilities and areas for improvement in the regulation.
  arXiv  Detail & Related papers  (2024-10-10T17:38:38Z)
• Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints [52.37099916582462]
  In Constrained Reinforcement Learning (CRL), agents explore the environment to learn the optimal policy while satisfying constraints. We propose a theoretically guaranteed penalty function method, Exterior Penalty Policy Optimization (EPO), with adaptive penalties generated by a Penalty Metric Network (PMN) PMN responds appropriately to varying degrees of constraint violations, enabling efficient constraint satisfaction and safe exploration.
  arXiv  Detail & Related papers  (2024-07-22T10:57:32Z)
• Automated legal reasoning with discretion to act using s(LAW) [0.294944680995069]
  ethical and legal concerns make it necessary for automated reasoners to justify in human-understandable terms. We propose to use s(CASP), a top-down execution model for predicate ASP, to model vague concepts following a set of patterns. We have implemented a framework, called s(LAW), to model, reason, and justify the applicable legislation and validate it by translating (and benchmarking) a representative use case.
  arXiv  Detail & Related papers  (2024-01-25T21:11:08Z)
• Informed AI Regulation: Comparing the Ethical Frameworks of Leading LLM Chatbots Using an Ethics-Based Audit to Assess Moral Reasoning and Normative Values [0.0]
  Ethics-based audits play a pivotal role in the rapidly growing fields of AI safety and regulation. This paper undertakes an ethics-based audit to probe the 8 leading commercial and open-source Large Language Models including GPT-4.
  arXiv  Detail & Related papers  (2024-01-09T14:57:30Z)
• Social, Legal, Ethical, Empathetic, and Cultural Rules: Compilation and Reasoning (Extended Version) [8.425874385897831]
  SLEEC (social, legal, ethical, empathetic, or cultural) rules aim to facilitate the formulation, verification, and enforcement of rules AI-based and autonomous systems should obey. To enable their effective use in AI systems, it is necessary to translate these rules systematically into a formal language that supports automated reasoning. In this study, we first conduct a linguistic analysis of the SLEEC rules pattern, which justifies the translation of SLEEC rules into classical logic.
  arXiv  Detail & Related papers  (2023-12-15T11:23:49Z)
• Learning Machine Morality through Experience and Interaction [3.7414804164475983]
  Increasing interest in ensuring safety of next-generation Artificial Intelligence (AI) systems calls for novel approaches to embedding morality into autonomous agents. We argue that more hybrid solutions are needed to create adaptable and robust, yet more controllable and interpretable agents.
  arXiv  Detail & Related papers  (2023-12-04T11:46:34Z)
• Formalizing the Problem of Side Effect Regularization [81.97441214404247]
  We propose a formal criterion for side effect regularization via the assistance game framework. In these games, the agent solves a partially observable Markov decision process. We show that this POMDP is solved by trading off the proxy reward with the agent's ability to achieve a range of future tasks.
  arXiv  Detail & Related papers  (2022-06-23T16:36:13Z)
• Transparency, Compliance, And Contestability When Code Is(n't) Law [91.85674537754346]
  Both technical security mechanisms and legal processes serve as mechanisms to deal with misbehaviour according to a set of norms. While they share general similarities, there are also clear differences in how they are defined, act, and the effect they have on subjects. This paper considers the similarities and differences between both types of mechanisms as ways of dealing with misbehaviour.
  arXiv  Detail & Related papers  (2022-05-08T18:03:07Z)
• Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning [131.1852444489217]
  This paper presents Object-aware REgularizatiOn (OREO), a technique that regularizes an imitation policy in an object-aware manner. Our main idea is to encourage a policy to uniformly attend to all semantic objects, in order to prevent the policy from exploiting nuisance variables strongly correlated with expert actions.
  arXiv  Detail & Related papers  (2021-10-27T01:56:23Z)
• Regularized Inverse Reinforcement Learning [49.78352058771138]
  Inverse Reinforcement Learning (IRL) aims to facilitate a learner's ability to imitate expert behavior. Regularized IRL applies strongly convex regularizers to the learner's policy. We propose tractable solutions, and practical methods to obtain them, for regularized IRL.
  arXiv  Detail & Related papers  (2020-10-07T23:38:47Z)
• Landscape of Machine Implemented Ethics [0.20305676256390928]
  This paper surveys the state-of-the-art in machine ethics, that is, considerations of how to implement ethical behaviour in robots, unmanned autonomous vehicles, or software systems. The emphasis is on covering the breadth of ethical theories being considered by implementors, as well as the implementation techniques being used. There is no consensus on which ethical theory is best suited for any particular domain, nor is there any agreement on which technique is best placed to implement a particular theory.
  arXiv  Detail & Related papers  (2020-09-01T10:34:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.