让模仿学习从记忆复刻转向可组合的长期适应能力。
Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning
- 用行为基元一次性学习，再组合应对新场景。
- 提出可组合泛化评估指标与混合架构设计。
- 适合研究开放世界智能体与认知启发式模型的人。
模仿学习面临关键瓶颈：尽管历经数十年发展，现有模仿学习智能体仍只是复杂的记忆机器，擅长重复已学行为，但在环境变化或目标演进时表现不佳。本文指出，这种失败并非技术缺陷，而是目标设定错误。我们主张将成功标准从完美复现转向可组合的适应能力，核心是通过一次学习行为基元，并在新情境中重新组合，无需重新训练。为此，我们建立了可组合泛化的评估指标，提出混合架构，并结合认知科学与文化演化，规划跨学科研究方向。将适应性嵌入模仿学习的核心，是智能体在开放世界中持续运作的关键能力。
原文摘要 · Abstract (English)
Imitation learning stands at a crossroads: despite decades of progress, current imitation learning agents remain sophisticated memorisation machines, excelling at replay but failing when contexts shift or goals evolve. This paper argues that this failure is not technical but foundational: imitation learning has been optimised for the wrong objective. We propose a research agenda that redefines success from perfect replay to compositional adaptability. Such adaptability hinges on learning behavioural primitives once and recombining them through novel contexts without retraining. We establish metrics for compositional generalisation, propose hybrid architectures, and outline interdisciplinary research directions drawing on cognitive science and cultural evolution. Agents that embed adaptability at the core of imitation learning thus have an essential capability for operating in an open-ended world.
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。