A coevolutionary approach to learn animal behavior through controlled interaction
A coevolutionary approach to learn animal behavior through controlled interaction
复制标题
通过受控交互学习动物行为的共同进化方法
DOI：
10.1145/2463372.2465801
复制
发表时间：
2013
期刊：
影响因子：
5.7
通讯作者：
R. Groß
中科院分区：
文献类型：
--
作者：
Wei Li;Melvin Gauci;R. Groß
这篇论文提出了一种方法，允许机器以全自动的方式推断动物的行为。原则上，机器不需要任何有关行为的先验信息。它能够改变环境条件，观察动物；因此，它可以通过受控互动了解动物。使用竞争性的协同进化方法，机器同时进化动物，即近似动物的模型，以及区分动物和动物的分类器。我们给出了一个在计算机模拟中进行的概念验证研究，证明了方法的可行性。此外，我们还表明，机器通过与动物互动比通过被动观察学习要好得多。我们讨论了该方法的优点和局限性，并概述了潜在的未来方向。
This paper proposes a method that allows a machine to infer the behavior of an animal in a fully automatic way. In principle, the machine does not need any prior information about the behavior. It is able to modify the environmental conditions and observe the animal; therefore it can learn about the animal through controlled interaction. Using a competitive coevolutionary approach, the machine concurrently evolves animats, that is, models to approximate the animal, as well as classifiers to discriminate between animal and animat. We present a proof-of-concept study conducted in computer simulation that shows the feasibility of the approach. Moreover, we show that the machine learns significantly better through interaction with the animal than through passive observation. We discuss the merits and limitations of the approach and outline potential future directions.