Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
复制标题
具有符号和像素输入的参考游戏中语言交流的出现
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
S. Clark
中科院分区：
文献类型：
--
作者：
Angeliki Lazaridou;Karl Moritz Hermann;K. Tuyls;S. Clark
算法进化或学习（组合）通信协议的能力传统上在语言进化文献中通过使用紧急通信任务进行研究。在这里，我们通过使用当代深度学习方法和在参考通信游戏上训练重复学习神经网络代理来扩大这项研究。我们扩展了以前的工作，其中代理在符号环境中进行训练，通过开发能够从原始像素数据中学习的代理，一个更具挑战性和现实的输入表示。我们发现，在输入数据中发现的结构的程度会影响出现的协议的性质，从而证实了这一假设，即结构化的组合语言是最有可能出现时，代理感知世界的结构。
The ability of algorithms to evolve or learn (compositional) communication protocols has traditionally been studied in the language evolution literature through the use of emergent communication tasks. Here we scale up this research by using contemporary deep learning methods and by training reinforcement-learning neural network agents on referential communication games. We extend previous work, in which agents were trained in symbolic environments, by developing agents which are able to learn from raw pixel data, a more challenging and realistic input representation. We find that the degree of structure found in the input data affects the nature of the emerged protocols, and thereby corroborate the hypothesis that structured compositional language is most likely to emerge when agents perceive the world as being structured.