McGraw Joshua D, Lee Donsuk, Wood Justin N
Department of Informatics, Indiana University Bloomington, Bloomington, IN, USA.
Cognitive Science Program, Indiana University Bloomington, Bloomington, IN, USA.
Nat Commun. 2024 Dec 5;15(1):10613. doi: 10.1038/s41467-024-52307-4.
Our algorithmic understanding of vision has been revolutionized by a reverse engineering paradigm that involves building artificial systems that perform the same tasks as biological systems. Here, we extend this paradigm to social behavior. We embodied artificial neural networks in artificial fish and raised the artificial fish in virtual fish tanks that mimicked the rearing conditions of biological fish. When artificial fish had deep reinforcement learning and curiosity-derived rewards, they spontaneously developed fish-like social behaviors, including collective behavior and social preferences (favoring in-group over out-group members). The artificial fish also developed social behavior in naturalistic ocean worlds, showing that these embodied models generalize to real-world learning contexts. Thus, animal-like social behaviors can develop from generic learning algorithms (reinforcement learning and intrinsic motivation). Our study provides a foundation for reverse-engineering the development of social behavior using image-computable models from artificial intelligence, bridging the divide between high-dimensional sensory inputs and collective action.
我们对视觉的算法理解因一种逆向工程范式而发生了革命性变化，该范式涉及构建执行与生物系统相同任务的人工系统。在此，我们将此范式扩展到社会行为。我们将人工神经网络体现在人工鱼中，并将人工鱼饲养在模拟生物鱼饲养条件的虚拟鱼缸中。当人工鱼进行深度强化学习并获得源自好奇心的奖励时，它们会自发地发展出类似鱼类的社会行为，包括集体行为和社会偏好（对内群体成员的偏好超过外群体成员）。人工鱼还在自然主义的海洋世界中发展出社会行为，表明这些具身模型能够推广到现实世界的学习情境中。因此，类似动物的社会行为可以从通用学习算法（强化学习和内在动机）中发展出来。我们的研究为使用人工智能的图像可计算模型对社会行为的发展进行逆向工程提供了基础，弥合了高维感官输入与集体行动之间的差距。
