Identifying Goals of Agents by Learning from Observations

Identifying Goals of Agents by Learning from Observations
复制标题

通过观察学习来确定智能体的目标

DOI:
10.1007/978-3-030-03014-8_11
复制
发表时间:
2018
期刊:
In: Proceedings of the 12th International Conference on Multi-disciplinary Trends in Artificial Intelligence (MIWAI 2018), Lecture Notes in Computer Science
影响因子:
--
通讯作者:
Katsumi Inoue
Katsumi Inoue
中科院分区:
--
文献类型:
--
作者:
Guillaume Lorthioir;Gauvain Bourgne;Katsumi Inoue

文献摘要

参考文献

被引文献

相似文献

意图识别问题是确定智能体意图和目标的一个难题。解决这个问题是有用的,当他们是几个代理人相互作用,当他们不知道对方。在这种情况下,可以提高代理人工作的效率。我们提出了一种方法来推断一个代理的可能目标,观察他在一系列成功的尝试,以达到他们。我们模型这个问题的概念学习的情况下,并提出了一个算法来产生简洁的假设。然而,这第一个建议没有考虑到我们的观察结果的连续性,我们讨论了当我们可以对代理的行为做出一些假设并使用环境动态的背景知识时,如何推断出更好的假设。然后,我们提供了一种简单的方法来丰富我们的数据,假设代理可以在下一步计算他的行为的影响,并在两个不同的设置中研究我们的建议的属性。我们表明,我们的算法将始终提供一个可能的目标,如果这样的目标存在(这意味着确实有一些状态,其中代理总是成功,并停止在我们的观察)。
The intention recognition problem is a difficult problem which consists in determining the intentions and the goals of an agent. Solving this problem is useful when they are several agents which are interacting with each other and when they do not know each other. The effectiveness of an agents’ work could be improved in this case. We present a method to infer the possible goals of an agent by observing him in a series of successful attempts to reach them. We model this problem as a case of concept learning and propose an algorithm to produce concise hypotheses. However, this first proposal does not take into account the sequential nature of our observations and we discuss how we can infer better hypotheses when we can make some assumption about the behavior of the agents and use background knowledge on the dynamics of the environment. We then provide a simple way to enrich our data by assuming the agent can compute the effects of his actions in the next step and study the properties of our proposal in two different settings. We show that our algorithm will always provide a possible goal if such a goal exists (meaning that there is indeed some set of states in which the agent always succeeds and stops in our observations).
在线目标识别作为地标推理
DOI: --
发表时间: 2018
期刊: AAAI Workshops
影响因子: --
作者:
Mor Vered;R. Pereira;M. Magnaguagno;Felipe Meneguzzi;G. Kaminka
通讯作者: G. Kaminka
MGI:增量自下而上算法
DOI: 10.1109/anziis.1994.396986
发表时间: 1994
期刊: Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference
影响因子: --
作者:
M. Henniche
通讯作者: M. Henniche
带有噪声观测的目标识别
DOI: --
发表时间: 2017
期刊: --
影响因子: --
作者:
Yolanda E;David E. Smith
通讯作者: David E. Smith
在计划识别中将领域理论和方法相结合
DOI: --
发表时间: 2017
期刊: --
影响因子: --
作者:
R. E. Cardona;R. Young
通讯作者: R. Young
对其他智能体行为的基于偏好的解释
DOI: --
发表时间: 2004
期刊: --
影响因子: --
作者:
J. Lang
通讯作者: J. Lang