PulseAugur
中
实时 02:23:02

新的MORL方法解决公平性和智能体协调问题

作者 PulseAugur 编辑部 · [4 个来源] ·

研究人员开发了用于多目标强化学习（MORL）的新方法，以解决公平性和协调性挑战。其中一篇论文介绍了在MORL中学习公平帕累托最优策略的算法，重点是通过适应历史不公平性来满足多样化的用户偏好。另一篇论文提出了用于合作多目标多智能体强化学习（MOMARL）的偏好协调多智能体策略优化（PCMA），能够协调智能体特定的偏好以提高团队绩效和权衡协调。 AI

影响 MORL和MOMARL的这些进展可能在复杂的多目标环境中带来更公平、更高效的决策系统。

排序理由 该集群包含两篇在arXiv上发表的学术论文，详细介绍了强化学习中的新算法和理论框架。

在 arXiv cs.MA (Multiagent) 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

新的MORL方法解决公平性和智能体协调问题

报道来源 [4]

  1. arXiv cs.AI TIER_1 English(EN) · Umer Siddique, Peilang Li, Yongcan Cao ·

    多目标强化学习中的公平帕累托最优策略学习

    arXiv:2606.18111v1 Announce Type: cross Abstract: Fairness is an important aspect of decision-making in multi-objective reinforcement learning (MORL), where policies must ensure both optimality and equity across multiple, potentially conflicting objectives. While single-policy MO…

  2. arXiv cs.AI TIER_1 English(EN) · Yongcan Cao ·

    多目标强化学习中的公平帕累托最优策略学习

    Fairness is an important aspect of decision-making in multi-objective reinforcement learning (MORL), where policies must ensure both optimality and equity across multiple, potentially conflicting objectives. While single-policy MORL methods can learn fair policies for fixed user …

  3. arXiv cs.AI TIER_1 English(EN) · Pengxin Wang, Lihao Guo, Yi Xie, Bo Liu, Siyang Cao, Jingdi Chen ·

    多目标多智能体强化学习中的协同偏好学习

    arXiv:2606.14693v1 Announce Type: cross Abstract: Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across ag…

  4. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Jingdi Chen ·

    多目标多智能体强化学习中的协同偏好学习

    Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this setting, conflicts arise not only across objectives but also across agents with different observations, roles, and contr…

相关实体

相关话题