Scholarlink

<p>As artificial intelligence (AI) systems are more widely deployed and utilized, they have greater potential to inflict harm or provide benefits to individuals. Designers must consider these concepts when building AI systems, but it is difficult to capture these notions in a mathematical framework. An ethical framework put forth by London and Heidari (Minds Mach, 2024. <a href="https://doi.org/10.1007/s11023-024-09696-8">https://doi.org/10.1007/s11023-024-09696-8</a>) provides structure and formal definitions of benefits and harms in relation to an individual’s life plans. This leaves an open question of how these concepts impact the decision-making of an AI system. We leverage their work to provide a direct translation of these theoretical ethical concepts to a standard multi-objective reinforcement learning (MORL) decision model. Using this model, we show that multi-objective rewards are <i>necessary</i> to capture benefits and harms in accordance with their definitions. We demonstrate how to capture these concepts in a MORL system and provide scenarios to highlight the utility of this work.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multi-objective reinforcement learning framework for beneficent artificial intelligence

  • 期刊论文

  • 发表日期：

    2025年6月8日

查看全文
  • Anna Nickelson,
  • Russell Perkins,
  • Alex John London,
  • Paul Robinette,
  • Kagan Tumer

摘要

As artificial intelligence (AI) systems are more widely deployed and utilized, they have greater potential to inflict harm or provide benefits to individuals. Designers must consider these concepts when building AI systems, but it is difficult to capture these notions in a mathematical framework. An ethical framework put forth by London and Heidari (Minds Mach, 2024. https://doi.org/10.1007/s11023-024-09696-8) provides structure and formal definitions of benefits and harms in relation to an individual’s life plans. This leaves an open question of how these concepts impact the decision-making of an AI system. We leverage their work to provide a direct translation of these theoretical ethical concepts to a standard multi-objective reinforcement learning (MORL) decision model. Using this model, we show that multi-objective rewards are necessary to capture benefits and harms in accordance with their definitions. We demonstrate how to capture these concepts in a MORL system and provide scenarios to highlight the utility of this work.