机器人通过好奇驱动探索，实现动作与语言的高效学习
Curiosity-Driven Development of Action and Language in Robots Through Self-Exploration
- 用好奇心驱动自探索，结合Q-learning实现内在动机学习
- 组合元素越多，泛化能力越强，学习速度显著提升
- 适合研究儿童语言发展与智能体自主学习的学者
婴儿能以极少经验实现语言泛化，而大语言模型需数十亿训练符号。本研究通过机器人实验，探究这一差异：机器人通过好奇驱动的自我探索，学习执行与祈使句（如‘推红方块’）相关动作。方法采用Q-learning近似主动推理，实现内在动机的发展性学习。模拟结果揭示关键发现：一、组合元素规模越大，泛化能力显著提升；二、好奇驱动探索加快学习进程；三、句子与动作的机械配对先于组合泛化出现；四、异常处理引发倒U型性能曲线，类似儿童语言学习中的表征重构现象。这些结果表明，好奇驱动的主动推理可解释人类及人工体在感知-运动-语言学习中如何实现可扩展的组合泛化与异常处理。
原文摘要 · Abstract (English)
Infants acquire language with generalization from minimal experience, whereas large language models require billions of training tokens. What underlies efficient development in humans? We investigated this problem through experiments wherein robotic agents learn to perform actions associated with imperative sentences (e.g., push red cube) via curiosity-driven self-exploration. Our approach amortizes active inference using Q-learning, enabling intrinsically motivated developmental learning. The simulations reveal key findings corresponding to observations in developmental psychology. i) Generalization improves drastically as the scale of compositional elements increases. ii) Curiosity-driven exploration enables faster learning. iii) Rote pairing of sentences and actions precedes compositional generalization. iv) Exception-handling induces U-shaped developmental performance, a pattern like representational redescription in child language learning. These results suggest that curiosity-driven active inference accounts for how intrinsically motivated sensorimotor-linguistic learning supports scalable compositional generalization and exception handling in humans and artificial agents.
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。