Nova : Value-based Negotiation of Norms
Nova : Value-based Negotiation of Norms
复制标题
Nova：基于价值的规范谈判
DOI：
10.1145/3465054
复制
发表时间：
2021
影响因子：
5
通讯作者：
Singh, Munindar P.
中科院分区：
文献类型：
--
作者：
Aydoğan, Reyhan;Kafali, Özgür;Arslan, Furkan;Jonker, Catholijn M.;Singh, Munindar P.
指定规范的多代理系统（nMAS）具有挑战性，因为不同的代理通常具有相互冲突的需求。虽然现有的方法可以解决明确削减的冲突，但在实践中，可能会在替代nMAS规范之间发生权衡，而没有明显的解决方案。为了产生每个代理都可以接受的nMAS规范，我们将规范过程建模为一组规范的协商。我们提出了一个基于agent的协商框架，其中agent的需求被表示为值(例如：（患者安全、隐私和国家安全），代理通过执行一组包含基于本体的推理的规范修订规则来修改nMAS规范，以促进其价值。为了证明我们的框架支持创建透明和可问责的mas规范，我们对与我们的代理进行谈判的人类参与者进行了实验。我们的研究结果表明，我们的谈判代理比基线策略更快地达成更好的协议（具有小值和大效应大小）。此外，参与者认为我们的代理比基线（在特定设置中具有小值和大效应大小）更能实现协作和透明的谈判，以达成协议。
Specifying a normative multiagent system (nMAS) is challenging, because different agents often have conflicting requirements. Whereas existing approaches can resolveclear-cutconflicts, tradeoffs might occur in practice among alternative nMAS specifications with no apparent resolution. To produce an nMAS specification that is acceptable to each agent, we model the specification process as a negotiation over a set of norms. We propose an agent-based negotiation framework, where agents’ requirements are represented asvalues(e.g., patient safety, privacy, and national security), and an agent revises the nMAS specification to promote its values by executing a set of norm revision rules that incorporate ontology-based reasoning. To demonstrate that our framework supports creating atransparentandaccountablenMAS specification, we conduct an experiment with human participants who negotiate against our agent. Our findings show that our negotiation agent reaches better agreements (with smallp-value and large effect size) faster than a baseline strategy. Moreover, participants perceive that our agent enables morecollaborativeand transparent negotiations than the baseline (with smallp-value and large effect size in particular settings) toward reaching an agreement.