An Experiment on Behavior Generalization and the Emergence of Linguistic Compositionality in Evolving Robots
An Experiment on Behavior Generalization and the Emergence of Linguistic Compositionality in Evolving Robots
复制标题
进化机器人中行为泛化和语言组合性出现的实验
DOI：
--
复制
发表时间：
2011
影响因子：
--
通讯作者：
S. Nolfi
中科院分区：
文献类型：
--
作者：
E. Tuci;Tomassino Ferrauto;Arne Zeschel;Gianluca Massera;S. Nolfi
由动态神经网络控制的模拟代理群体通过人工进化训练来获取语言指令，并通过指示、触摸或移动特定目标物体来执行这些指令。在训练过程中，智能体只经历所有对象/动作对的一个子集。在后评估期间，一些成功的代理人被证明能够访问和执行训练期间没有经历过的语言指令。这要归功于语义空间的发展，它以智能体的感觉运动能力为基础，并以系统化的方式组织起来，以促进语言的组合性和行为的泛化。组合性似乎是由代理访问和执行指令的能力所支撑的，这种能力是通过暂时地将它们的语言和行为方面分解成它们的组成部分（即，找到目标对象并执行所需的操作）来实现的。在一种实验条件下，智能体被要求忽略而不是指示对象，这两种实验条件的比较表明，行为集的组成显著影响组合语义结构的发展。
Populations of simulated agents controlled by dynamical neural networks are trained by artificial evolution to access linguistic instructions and to execute them by indicating, touching, or moving specific target objects. During training the agent experiences only a subset of all object/action pairs. During postevaluation, some of the successful agents proved to be able to access and execute also linguistic instructions not experienced during training. This owes to the development of a semantic space, grounded in the sensory motor capability of the agent and organized in a systematized way in order to facilitate linguistic compositionality and behavioral generalization. Compositionality seems to be underpinned by a capability of the agents to access and execute the instructions by temporally decomposing their linguistic and behavioral aspects into their constituent parts (i.e., finding the target object and executing the required action). The comparison between two experimental conditions, in one of which the agents are required to ignore rather than to indicate objects, shows that the composition of the behavioral set significantly influences the development of compositional semantic structures.
影响因子：
2.2
作者：
Macwhinney,Brian
通讯作者：
Macwhinney,Brian