Human infants acquire language and action gradually through development, achieving remarkable generalization capabilities from only a minimal number of learning examples. In contrast, recent large language models require exposure to billions of training tokens to achieve such generalization. What mechanisms underlie such efficient developmental learning in humans? This study addresses this question through simulation experiments in which robots learn to perform various actions corresponding to imperative sentences (e.g., \textit{push red cube}) via trials of self-guided exploration. Our approach integrates the active inference framework with reinforcement learning, enabling curiosity-driven developmental learning. The simulations yielded several important findings: i) Generalization is drastically improved as the number of compositional elements increases. ii) Curiosity-driven exploration combined with motor noise substantially outperforms learning without curiosity. iii) Rote pairing of sentences and actions occurs before the emergence of compositional generalization. iv) Simpler, prerequisite-like actions emerge earlier in development, while more complex actions involving these prerequisites develop later. These results shed light into possible mechanisms underlying efficient developmental learning in infants and provide computational parallels to findings in developmental psychology.

翻译：人类婴儿通过发育过程逐步习得语言和动作，仅需极少量的学习样本就能获得卓越的泛化能力。相比之下，近期的大型语言模型需要接触数十亿的训练标记才能达到类似的泛化水平。人类这种高效发育学习的机制是什么？本研究通过仿真实验探讨该问题：机器人通过自我引导探索的尝试，学习执行与祈使句（例如\textit{push red cube}）对应的各种动作。我们的方法将主动推理框架与强化学习相结合，实现了好奇心驱动的发育学习。仿真实验得出若干重要发现：i) 随着组合元素数量的增加，泛化能力显著提升。ii) 好奇心驱动探索结合运动噪声的表现远超无好奇心的学习。iii) 句子与动作的机械配对出现在组合泛化形成之前。iv) 更简单、类似先决条件的动作在发育早期出现，而包含这些先决条件的更复杂动作则在后期形成。这些结果揭示了婴儿高效发育学习的可能机制，并为发展心理学的研究发现提供了计算层面的参照。