研究人员开发了一种名为适应性惩罚促进合作（APC）的新方法，以鼓励在混合动机博弈中的合作。APC根据背叛的严重程度动态调整惩罚的强度和概率，旨在减少代价高昂且无效的惩罚。该方法使用背叛意识模块，在游戏奖励的指导下评估背叛的严重程度。理论和实证结果表明，APC在迭代公共物品博弈和其他社会困境中能有效促进合作，优于现有方法。 AI
影响 引入了一种促进多智能体系统中合作的新策略，有可能改善涉及自利智能体的场景中的结果。
排序理由 该集群包含一篇详细介绍多智能体系统新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.24516v1 Announce Type: cross Abstract: Mixed-motive scenarios are ubiquitous in real-world multi-agent interactions, where self-interested agents often defect for immediate rewards, overlooking the potential of altruistic cooperation to improve long-term gains and coll…
Mixed-motive scenarios are ubiquitous in real-world multi-agent interactions, where self-interested agents often defect for immediate rewards, overlooking the potential of altruistic cooperation to improve long-term gains and collective welfare. Peer punishment can deter defectio…