Human-aligned artificial intelligence is a multiobjective problem

No abstract is available for this paper.

• Publication year

  2017

• Venue

  Ethics and Information Technology

• Publication date

  2017-10-04

• Fields of study

  Philosophy, Computer Science

• Identifiers
  DOI 10.1007/s10676-017-9440-6
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Utility theory

  2019cited by this paper
• Introduction I

  2018cited by this paper
• Toward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making

  2017cited by this paper
• IEEE standard review — Ethically aligned design: A vision for prioritizing human wellbeing with artificial intelligence and autonomous systems

  2017cited by this paper
• Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures

  2016cited by this paper
• Designing AI systems that obey our laws and values

  2016cited by this paper
• Concrete Problems in AI Safety

  2016influential reference
• Quantilizers: A Safer Alternative to Maximizers for Limited Optimization

  2016influential reference
• Service robots, care ethics, and design

  2016cited by this paper
• Mastering the game of Go with deep neural networks and tree search

  2016cited by this paper
• Reinforcement Learning as a Framework for Ethical Decision Making

  2016cited by this paper
• Robot Ethics: The Ethical and Social Implications of Robotics

  2016cited by this paper
• Using Stories to Teach Human Values to Artificial Agents

  2016cited by this paper
• The ethics of algorithms: Mapping the debate

  2016cited by this paper
• On how AI & Law can help autonomous systems obey the law: a position paper

  2016cited by this paper
• Creating Socially Adaptive Electronic Partners: Interaction, Reasoning and Ethical Challenges

  2015cited by this paper
• Human-level control through deep reinforcement learning

  2015cited by this paper
• Corrigibility

  2015cited by this paper
• Aligning Superintelligence with Human Interests: A Technical Research Agenda

  2015cited by this paper
• Reinforcement learning improves behaviour from evaluative feedback

  2015cited by this paper
• Letter to the Editor: Research Priorities for Robust and Beneficial Artificial Intelligence: An Open Letter

  2015cited by this paper
• Reinforcement Learning and the Reward Engineering Principle

  2014cited by this paper
• Limitations and risks of machine ethics

  2014cited by this paper
• A novel adaptive weight selection algorithm for multi-objective multi-agent reinforcement learning

  2014cited by this paper
• Superintelligence: Paths, Dangers, Strategies

  2014influential reference
• Laws on Robots, Laws by Robots, Laws in Robots: Regulating Robot Behaviour by Design

  2014cited by this paper
• The First Level of Super Mario Bros . is Easy with Lexicographic Orderings and Time Travel

  2013cited by this paper
• A multidisciplinary survey on discrimination analysis

  2013cited by this paper
• Arms control for armed uninhabited vehicles: an ethical issue

  2013cited by this paper
• A Survey of Multi-Objective Sequential Decision-Making

  2013cited by this paper
• Moral Machines: Teaching Robots Right from Wrong

  2012influential reference
• Normative Multi-Agent Systems

  2012cited by this paper
• Introduction to "This is Watson"

  2012cited by this paper
• Thinking Inside the Box: Controlling and Using an Oracle AI

  2012cited by this paper
• Killing Made Easy: From Joysticks to Politics

  2012cited by this paper
• The Rights and Wrongs of Robot Care

  2012cited by this paper
• Moral Machines: Contradiction in Terms or Abdication of Human Responsibility?

  2012cited by this paper
• A Body to Kick, but Still No Soul to Damn: Legal Perspectives on Robotics

  2012cited by this paper
• Evolving policies for multi-reward partially observable markov decision processes (MR-POMDPs)

  2011cited by this paper
• Learning What to Value

  2011cited by this paper
• Ethics

  2011cited by this paper
• Ethics and Technology: Controversies, Questions, and Strategies for Ethical Computing

  2010cited by this paper
• Learning controllers for human-robot interaction

  2009cited by this paper
• Can robots have a conscience?

  2009cited by this paper
• Multiple objective ant colony optimisation

  2009cited by this paper
• Death strikes from the sky: the calculus of proportionality

  2009cited by this paper
• On the Broad Implications of Reinforcement Learning based AGI

  2008cited by this paper
• The Basic AI Drives

  2008influential reference
• Moral Machines: Teaching Robots Right from Wrong

  2008influential reference
• Governing lethal behavior: Embedding ethics in a hybrid deliberative/reactive robot architecture part I: Motivation and philosophy

  2008cited by this paper
• On the Limitations of Scalarisation for Multi-objective Reinforcement Learning of Pareto Fronts

  2008cited by this paper
• Machine Ethics: Creating an Ethical Intelligent Agent

  2007cited by this paper
• MedEthEx: A Prototype Medical Ethics Advisor

  2006cited by this paper
• An Approach to Computing Ethics

  2006cited by this paper
• Evolutionary multi-objective optimization: a historical view of the field

  2006cited by this paper
• Evolutionary multi-objective optimization: a historical view of the field

  2006cited by this paper
• Particularism and the Classification and Reclassification of Moral Cases

  2006cited by this paper
• Multi-Objective Particle Swarm Optimisation Methods

  2004cited by this paper
• Lego Mindstorms Robots as a Platform for Teaching Reinforcement Learning

  2004cited by this paper
• Multiobjective heuristic state-space planning

  2003cited by this paper
• Ethics in Information Technology

  2002cited by this paper
• Goal generation in the BOID architecture

  2002cited by this paper
• Decision-Theoretic Planning

  1999cited by this paper
• Deliberative Normative Agents: Principles and Architecture

  1999cited by this paper
• Introduction to Reinforcement Learning

  1998cited by this paper
• Reinforcement Learning: An Introduction

  1998cited by this paper
• A closer look at drawbacks of minimizing weighted sums of objectives for Pareto set generation in multicriteria optimization problems

  1997cited by this paper
• Beyond min aggregation in multicriteria decision: (ordered) weighted min, discri-min, leximin

  1997cited by this paper
• Autonomous agents and social norms

  1996cited by this paper
• Autonomous Robot Vehicles

  1990cited by this paper
• National Aeronautics and

  1990cited by this paper
• Value-driven expert systems for decision support

  1988cited by this paper
• REASONING ABOUT PREFERENCE MODELS

  1985cited by this paper
• EURISKO: A Program That Learns New Heuristics and Domain Concepts

  1983cited by this paper
• Grounding for the metaphysics of morals

  1981cited by this paper
• A Theory of Justice

  1971cited by this paper
• The Right and the Good

  year unknowncited by this paper
• Research priorities for robust and beneficial artificial intelligence

  year unknowncited by this paper

• From Vulnerable to Resilient: Examining Parent and Teen Perceptions on How to Respond to Unwanted Cybergrooming Advances

  2026cites this paper
• Multi-objective reinforcement learning for provably incentivising alignment with value systems

  2026cites this paper
• ADAPTIVE AI-TUTORS FOR THEATRE AND DRAMA EDUCATION

  2026cites this paper
• Learning the Value Systems of Societies with Preference-based Multi-objective Reinforcement Learning

  2026cites this paper
• Reward-free Alignment for Conflicting Objectives

  2026cites this paper
• Learning the value systems of agents with preference-based and inverse reinforcement learning

  2026cites this paper
• Against AI ethics: challenging the conventional narratives

  2026cites this paper
• Multi-objective Large Language Model Alignment with Hierarchical Experts

  2025cites this paper
• Ethically Responsible Decision Making for Anomaly Detection in Complex Driving Scenes

  2025cites this paper
• Exploring Cognitive Attributes in Financial Decision-Making

  2025cites this paper
• Navigating the Nexus of ethical standards and moral values

  2025cites this paper
• “Turning right”? An experimental study on the political value shift in large language models

  2025cites this paper
• The Moral Uncanny Valley

  2025cites this paper
• Decision-Making in the Age of AI: A Review of Theoretical Frameworks, Computational Tools, and Human-Machine Collaboration

  2025cites this paper
• Collab: Controlled Decoding using Mixture of Agents for LLM Alignment

  2025cites this paper
• The Four Fundamental Components for Intelligibility and Interpretability in AI Ethics

  2025cites this paper
• Robust Multi-Objective Controlled Decoding of Large Language Models

  2025cites this paper
• Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?

  2025cites this paper
• The Specification Trap: Why Content-Based AI Value Alignment Cannot Produce Robust Alignment

  2025cites this paper
• An Approximate Embedding for Designing Ethical Reinforcement Learning Environments

  2025cites this paper
• Individual utilities of life satisfaction reveal inequality aversion unrelated to political alignment

  2025cites this paper
• Making AI Tutors Empathetic and Conscious: A Needs-Driven Pathway to Synthetic Machine Consciousness

  2025cites this paper
• Multi-objective reinforcement learning framework for beneficent artificial intelligence

  2025cites this paper
• Towards algorithms and models that we can trust: A theoretical perspective

  2024cites this paper
• Hindsight PRIORs for Reward Learning from Human Preferences

  2024cites this paper
• Learning Adaptive Multi-Objective Robot Navigation with Demonstrations

  2024cites this paper
• Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization

  2024cites this paper
• Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

  2024cites this paper
• Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning

  2024cites this paper
• When tomorrow comes: A prospective risk assessment of a future artificial general intelligence-based uncrewed combat aerial vehicle system.

  2024cites this paper
• From the Pascal Wager to Value Engineering: A Glance at AI Risks and How to Address Them

  2024cites this paper
• GAMA CUTE: Development of a Web-based for Gadjah Mada Caring University for Thalassemia Exit Prediction Tool by Applying Machine Learning

  2024cites this paper
• Competing narratives in AI ethics: a defense of sociotechnical pragmatism

  2024cites this paper
• AI apology: a critical review of apology in AI systems

  2024cites this paper
• Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI

  2024cites this paper
• The World is a Multi-Objective Multi-Agent System: Now What?

  2024cites this paper
• Personalized Adaptation via In-Context Preference Learning

  2024cites this paper
• Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment

  2024cites this paper
• GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment

  2024cites this paper
• Intuitions of Compromise: Utilitarianism vs. Contractualism

  2024cites this paper
• Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization

  2024cites this paper
• Demonstration-Enhanced Adaptable Multi-Objective Robot Navigation

  2024cites this paper
• A Novel Multi-Objective Deep Q-Network: Addressing Immediate and Delayed Rewards in Multi-Objective Q-Learning

  2024cites this paper
• Dynamic preference inference network: Improving sample efficiency for multi-objective reinforcement learning by preference estimation

  2024cites this paper
• A Deep Reinforcement Learning-Based Method for Dynamic Quality of Service aware Energy and Occupant Comfort Management in Intelligent Buildings

  2024cites this paper
• Towards Value Alignment for Opaque Agents Through Concept Analysis and Inter-Agent Value Modelling

  2024cites this paper
• Reinforcement Learning and Machine ethics:a systematic review

  2024cites this paper
• Decoding-Time Language Model Alignment with Multiple Objectives

  2024cites this paper
• Cascade Reward Sampling for Efficient Decoding-Time Alignment

  2024cites this paper
• Strategies for Compressing the Pareto Frontier: Application to Strategic Planning of Hydropower in the Amazon Basin

  2024cites this paper
• An evaluation of estimative uncertainty in large language models

  2024cites this paper
• Is It AI or Is It Me? Understanding Users’ Prompt Journey with Text-to-Image Generative AI Tools

  2024cites this paper
• Testing System Intelligence

  2023cites this paper
• Health condition monitoring of a complex hydraulic system using Deep Neural Network and DeepSHAP explainable XAI

  2023cites this paper
• Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning

  2023cites this paper
• Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning

  2023cites this paper
• A State Augmentation based approach to Reinforcement Learning from Human Preferences

  2023cites this paper
• Data Driven Reward Initialization for Preference based Reinforcement Learning

  2023cites this paper
• Ethical content in artificial intelligence systems: A demand explained in three critical points

  2023cites this paper
• AI apology: interactive multi-objective reinforcement learning for human-aligned AI

  2023cites this paper
• Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation

  2023cites this paper
• Scalar Reward is Not Enough

  2023cites this paper
• A Brief Guide to Multi-Objective Reinforcement Learning and Planning

  2023cites this paper
• Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

  2023cites this paper
• Aligning Human Preferences with Baseline Objectives in Reinforcement Learning

  2023cites this paper
• Ethical issues in the development of artificial intelligence: recognizing the risks

  2023cites this paper
• Onset of a conceptual outline map to get a hold on the jungle of cluster analysis

  2023cites this paper
• What Lies beyond the Pareto Front? A Survey on Decision-Support Methods for Multi-Objective Optimization

  2023cites this paper
• Artificial intelligence and conversational agent evolution - a cautionary tale of the benefits and pitfalls of advanced technology in education, academic research, and practice

  2023cites this paper
• The Roles and Modes of Human Interactions with Automated Machine Learning Systems: A Critical Review and Perspectives

  2023cites this paper
• Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

  2023cites this paper
• Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto

  2023influential citation
• Multi-objective reinforcement learning for designing ethical multi-agent environments

  2023cites this paper
• Learning to identify and settle dilemmas through contextual user preferences

  2023cites this paper
• Reinforcement Learning Guided by Provable Normative Compliance

  2022cites this paper
• Sustainable AI: An integrated model to guide public sector decision-making

  2022cites this paper
• Contextual bandits with concave rewards, and an application to fair ranking

  2022cites this paper
• Using soft maximin for risk averse multi-objective decision-making

  2022influential citation
• The Legacy of Peter Fishburn: Foundational Work and Lasting Impact

  2022cites this paper
• Business and/or Ethics? A Framework for Resolving Multicriteria Decision Dilemmas

  2022cites this paper
• Improving performance in multi-objective decision-making in Bottles environments with soft maximin approaches

  2022influential citation
• Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learning

  2022cites this paper
• Artificial Intelligence in Education: Fears and Faiths

  2022cites this paper
• Racing into the fourth industrial revolution: exploring the ethical dimensions of medical AI and rights-based regulatory framework

  2022cites this paper
• A multi‐objective multi‐agent deep reinforcement learning approach to residential appliance scheduling

  2022cites this paper
• Near On-Policy Experience Sampling in Multi-Objective Reinforcement Learning

  2022cites this paper
• Ec-Funded Projects’ Lessons Learned In Earth Friendly Freight Transportation

  2022cites this paper
• Choosing Ethics Over Morals: A Possible Determinant to Embracing Artificial Intelligence in Future Urban Mobility

  2021cites this paper
• Human-Centered AI

  2021cites this paper
• HUMAN FACTORS AND ERGONOMICS IN DESIGN OF A 3 : AUTOMATION, AUTONOMY, AND ARTIFICIAL INTELLIGENCE

  2021cites this paper
• Methodological analysis of the personnel training pedagogical space in the agro-industrial complex

  2021cites this paper
• Artificial intelligence and mass personalization of communication content—An ethical and literacy perspective

  2021cites this paper
• Impossibility Results in AI: A Survey

  2021cites this paper
• Explainable reinforcement learning for broad-XAI: a conceptual framework and survey

  2021influential citation
• Moral Disagreement and Artificial Intelligence

  2021cites this paper
• Ethical Artificial Intelligence in Chemical Research and Development: A Dual Advantage for Sustainability

  2021cites this paper
• Levels of explainable artificial intelligence for human-aligned conversational explanations

  2021cites this paper
• Artificial intelligence in drug design: algorithms, applications, challenges and ethics

  2021cites this paper
• Leveraging Artificial Intelligence in Marketing for Social Good—An Ethical Perspective

  2021cites this paper
• Guaranteeing the Learning of Ethical Behaviour through Multi-Objective Reinforcement Learning

  2021cites this paper