论文标题
查看，听到，探索：通过视听协会的好奇心
See, Hear, Explore: Curiosity via Audio-Visual Association
论文作者
论文摘要
探索是加强学习的核心挑战之一。好奇心驱动的探索的共同表述使用了真正的未来与被学识渊博的模型预测的未来之间的差异。但是，预测未来是一项本质上困难的任务，面对随机性，可能会犯下不足的任务。在本文中，我们引入了一种好奇心的另一种形式，可以奖励不同感官之间的新型关联。我们的方法利用了多种方式，为更有效的探索提供了更强的信号。我们的方法的灵感来自于人类在探索中起着关键作用的事实。我们在几个Atari环境和栖息地（一个逼真的导航模拟器）上介绍了结果，显示了在没有外部奖励的情况下使用音频视频关联模型来本质上指导学习剂的好处。有关视频和代码，请参见https://vdean.github.io/audio-curiosity.html。
Exploration is one of the core challenges in reinforcement learning. A common formulation of curiosity-driven exploration uses the difference between the real future and the future predicted by a learned model. However, predicting the future is an inherently difficult task which can be ill-posed in the face of stochasticity. In this paper, we introduce an alternative form of curiosity that rewards novel associations between different senses. Our approach exploits multiple modalities to provide a stronger signal for more efficient exploration. Our method is inspired by the fact that, for humans, both sight and sound play a critical role in exploration. We present results on several Atari environments and Habitat (a photorealistic navigation simulator), showing the benefits of using an audio-visual association model for intrinsically guiding learning agents in the absence of external rewards. For videos and code, see https://vdean.github.io/audio-curiosity.html.
