让智能体主动寻求理解与被理解，促进合作行为
Wanting to be Understood
- 用内在奖励模拟人类理解与被理解的驱动力
- 强调互惠理解的奖励使智能体更愿互动
- 适合研究社交智能与合作机制的学者
本文探究了人类内在的相互认知动机，假设即使在没有外部奖励的情况下，人们仍具有理解他人和被他人理解的基本驱动力。通过感知交叉范式模拟，我们测试了强化学习智能体中不同内在奖励函数的效果。理解的驱动力以主动推断型人工好奇心奖励实现，被理解的驱动力则通过模仿、影响/易受影响性以及对他人反应时间的预期等内在奖励体现。结果表明，仅靠人工好奇心无法引发对社交互动的偏好，而强调互惠理解的奖励能有效驱动智能体优先选择互动。我们证明，这种内在动机可在仅一个智能体获得外部奖励的合作任务中促进协作。
原文摘要 · Abstract (English)
This paper explores an intrinsic motivation for mutual awareness, hypothesizing that humans possess a fundamental drive to understand and to be understood even in the absence of extrinsic rewards. Through simulations of the perceptual crossing paradigm, we explore the effect of various internal reward functions in reinforcement learning agents. The drive to understand is implemented as an active inference type artificial curiosity reward, whereas the drive to be understood is implemented through intrinsic rewards for imitation, influence/impressionability, and sub-reaction time anticipation of the other. Results indicate that while artificial curiosity alone does not lead to a preference for social interaction, rewards emphasizing reciprocal understanding successfully drive agents to prioritize interaction. We demonstrate that this intrinsic motivation can facilitate cooperation in tasks where only one agent receives extrinsic reward for the behaviour of the other.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。