Emergence of Gricean Maxims from Multi-Agent Decision Theory
Emergence of Gricean Maxims from Multi-Agent Decision Theory
复制标题
多智能体决策理论中格里斯准则的出现
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Dan Jurafsky
中科院分区：
文献类型：
--
作者：
Adam Vogel;Max Bodoia;Christopher Potts;Dan Jurafsky
格赖斯用合作原则来描述沟通，这一原则要求说话者只做出有利于不断发展的对话目标的贡献。我们证明了合作原则和相关的相关性、质量和数量准则是从多智能体决策理论中产生的。我们利用分散式部分可观察马尔可夫决策过程（deco - pomdp）模型进行多智能体决策，该模型仅依赖于理性的基本定义和智能体相互推理共同效用最大化信念的能力。我们的模型使用认知启发的启发式来简化对行动、环境和其他参与者的嵌套信念进行联合推理的其他棘手任务。我们对合作语言任务的实验表明，对他人信念状态的推理，以及由此产生的Gricean交际行为，显著提高了任务绩效。
Grice characterized communication in terms of the cooperative principle, which enjoins speakers to make only contributions that serve the evolving conversational goals. We show that the cooperative principle and the associated maxims of relevance, quality, and quantity emerge from multi-agent decision theory. We utilize the Decentralized Partially Observable Markov Decision Process (Dec-POMDP) model of multi-agent decision making which relies only on basic definitions of rationality and the ability of agents to reason about each other’s beliefs in maximizing joint utility. Our model uses cognitively-inspired heuristics to simplify the otherwise intractable task of reasoning jointly about actions, the environment, and the nested beliefs of other actors. Our experiments on a cooperative language task show that reasoning about others’ belief states, and the resulting emergent Gricean communicative behavior, leads to significantly improved task performance.
影响因子：
4.3
作者：
Thomson, Blaise;Young, Steve
通讯作者：
Young, Steve