We propose a novel framework to learn how to communicate with intent, i.e., to transmit messages over a wireless communication channel based on the end-goal of the communication. This stays in stark contrast to classical communication systems where the objective is to reproduce at the receiver side either exactly or approximately the message sent by the transmitter, regardless of the end-goal. Our procedure is general enough that can be adapted to any type of goal or task, so long as the said task is a (almost-everywhere) differentiable function over which gradients can be propagated. We focus on supervised learning and reinforcement learning (RL) tasks, and propose algorithms to learn the communication system and the task jointly in an end-to-end manner. We then delve deeper into the transmission of images and propose two systems, one for the classification of images and a second one to play an Atari game based on RL. The performance is compared with a joint source and channel coding (JSCC) communication system designed to minimize the reconstruction error, and results show overall great improvement. Further, for the RL task, we show that while a JSCC strategy is not better than a random action selection strategy, with our approach we get close to the upper bound even for low SNRs.
翻译:我们提出一个新的框架,学习如何以意向方式,即根据通信的最终目的,通过无线通信频道传递信息。这与传统通信系统形成鲜明对比,传统通信系统的目标是在接收方准确或大致复制发报机发送的信息,而不管最终目标如何。我们的程序很笼统,可以适应任何类型的目标或任务,只要所述任务是一个(几乎几乎每个地方)可传播梯度的可不同功能。我们侧重于监督的学习和加强学习(RL)任务,并提出算法,以端到端的方式共同学习通信系统和任务。我们然后更深入地研究图像的传输,提出两个系统,一个用于图像分类,第二个用于播放基于RL的阿塔里游戏。 业绩与联合源和频道连接(JSCC)通信系统进行比较,以尽量减少重建错误,结果显示总体的极大改进。此外,对于我们的任务来说,我们展示的是,即使联合通信委员会的战略比随机选择战略的上限更好。