How have individuals of social animals in nature evolved to learn from each other, and what would be the optimal strategy for such learning in a specific environment? Here, we address both problems by employing a deep reinforcement learning model to optimize the social learning strategies (SLSs) of agents in a cooperative game in a multi-dimensional landscape. Throughout the training for maximizing the overall payoff, we find that the agent spontaneously learns various concepts of social learning, such as copying, focusing on frequent and well-performing neighbors, self-comparison, and the importance of balancing between individual and social learning, without any explicit guidance or prior knowledge about the system. The SLS from a fully trained agent outperforms all of the traditional, baseline SLSs in terms of mean payoff. We demonstrate the superior performance of the reinforcement learning agent in various environments, including temporally changing environments and real social networks, which also verifies the adaptability of our framework to different social settings.

翻译：自然界中的社会性动物个体如何演化出相互学习的能力？在特定环境中，这种学习的最优策略又是什么？本文通过采用深度强化学习模型，优化多维景观合作博弈中智能体的社会学习策略，同时解决这两个问题。在追求整体收益最大化的训练过程中，我们发现智能体无需任何系统显式指导或先验知识，即可自发习得社会学习的多种概念，包括模仿、关注高频率且表现优异的邻居、自我比较，以及平衡个体学习与社会学习的重要性。经过充分训练后的智能体所采用的社会学习策略，在平均收益上优于所有传统基线社会学习策略。我们进一步在多种环境（包括时间变化环境及真实社交网络）中验证了该强化学习智能体的卓越性能，这同时证实了我们的框架在不同社会情境下的适应能力。