Efficient Querying for Cooperative Probabilistic Commitments
Efficient Querying for Cooperative Probabilistic Commitments
复制标题
合作概率承诺的高效查询
DOI：
10.1609/aaai.v35i13.17356
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Satinder Singh
中科院分区：
文献类型：
--
作者：
Qi Zhang;E. Durfee;Satinder Singh
多智能体系统可以使用承诺作为一般协调基础设施的核心，支持合作和非合作交互。目标一致的智能体，如果一个智能体可以通过牺牲自己的一些回报来帮助另一个智能体获得更大的回报，就应该选择合作承诺来最大化他们的共同回报。我们提出了一个解决方案的问题，合作代理如何有效地找到一个（近似）最优的承诺，通过查询精心选择的承诺选择。我们证明了代理值的结构属性作为承诺规范参数的函数，并开发了一种贪心方法，用于组合具有可证明的近似边界的查询，我们经验地表明，该方法可以在缺乏我们洞察力的方法所需的一小部分时间内找到几乎最优的承诺。
Multiagent systems can use commitments as the core of a general coordination infrastructure, supporting both cooperative and non-cooperative interactions. Agents whose objectives are aligned, and where one agent can help another achieve greater reward by sacrificing some of its own reward, should choose a cooperative commitment to maximize their joint reward. We present a solution to the problem of how cooperative agents can efficiently find an (approximately) optimal commitment by querying about carefully-selected commitment choices. We prove structural properties of the agents' values as functions of the parameters of the commitment specification, and develop a greedy method for composing a query with provable approximation bounds, which we empirically show can find nearly optimal commitments in a fraction of the time methods that lack our insights require.