强弱例外下的交互时态逻辑  

Alternating-time temporal logic with strong and weak exceptions

作　　者：赖贤伟[1] 胡山立[2,3] 宁正元[1] 王秀丽[1] 

机构地区：[1]福建农林大学计算机与信息学院,福州350002 [2]福州大学数学与计算机科学学院,福州350002 [3]中国科学院计算机科学重点实验室,北京100080

出　　处：《计算机应用》2008年第11期2874-2876,2886,共4页journal of Computer Applications

基　　金：国家自然科学基金资助项目(6037307960573076);中国科学院计算机科学重点实验室开放课题基金资助项目(SYSKF0505);福建省自然科学基金资助项目(2006J02992006J0018);校青年教师科研基金资助项目(08B21)

摘　　要：非单调推理是众多人工智能应用系统都可能面对的问题,多Agent系统也不例外。在前期关于AgentBD I逻辑、多Agent合作逻辑、多Agent合作问题求解过程建模等研究工作的基础上,借鉴Baral等人开发非单调线性时态逻辑N-LTL的技术,利用强弱例外对多Agent合作逻辑的开创性工作交互时态逻辑(ATL)进行拓展,建立非单调交互时态逻辑NATL,给出其语法和语义。是对ATL进行非单调拓展的首次有益尝试。可以考虑以之为理论工具对多Agent思维状态及其动态修正机制进行妥善刻画。Most application systems of artificial intelligence may face the problem of non-monotonic reasoning, so do multi-agent systems. Based on our former work on agent BDI logic, multi-agent cooperation logics and multi-agent cooperative problem solving process modeling, as well as the work of Baral et al. on non-monotonic temporal logics, strong and weak exceptions were introduced to Ahernating-time Temporal Logic （ATL） that was the primogenitor of muhi-agent cooperation logics. As a result, non-monotonic alternating-time temporal logic was developed, and its syntax and semantics were proposed. As far as we know, the work presented in this paper was the first attempt of non-monotonic extending of muhi-agent cooperation logics. Non-monotonic alternating-time temporal logic can be adopted as a theoretical tool to model multi-agent mental states and their dynamic revision mechanism.

关 键 词：多AGENT系统 非单调逻辑 交互时态逻辑 并发博弈结构 目标 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]