可检索技能增量学习用于高效持续任务适应
Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
AI总结：
针对持续模仿学习中适配器方法限制知识共享的问题，提出IsCiL框架，通过增量学习可共享技能并基于原型记忆检索，实现非平稳环境下的样本高效任务适应，实验验证了其稳健性能。
摘要：
持续模仿学习（CiL）涉及从多个阶段和任务的示范中提取并积累任务知识，以实现多任务策略。随着基础模型的最新进展，基于适配器的CiL方法日益受到关注，其中为新示范任务以参数高效的方式建立适配器。虽然这些方法为特定任务隔离参数并倾向于缓解灾难性遗忘，但它们限制了不同示范之间的知识共享。我们提出了IsCiL，一种基于适配器的CiL框架，通过从不同示范中增量学习可共享技能来解决这一知识共享限制，从而在非平稳CiL环境中特别利用这些技能实现样本高效的任务适应。在IsCiL中，示范被映射到状态嵌入空间，其中适当的技能可通过基于原型的记忆根据输入状态进行检索。这些可检索技能在其对应的适配器上增量学习。我们在Franka-Kitchen和Meta-World中进行的复杂任务CiL实验证明了IsCiL在任务适应和样本效率方面的稳健性能。我们还展示了IsCiL在任务遗忘场景中的简单扩展。
英文摘要：
Continual Imitation Learning (CiL) involves extracting and accumulating task knowledge from demonstrations across multiple stages and tasks to achieve a multi-task policy. With recent advancements in foundation models, there has been a growing interest in adapter-based CiL approaches, where adapters are established parameter-efficiently for tasks newly demonstrated. While these approaches isolate parameters for specific tasks and tend to mitigate catastrophic forgetting, they limit knowledge sharing among different demonstrations. We introduce IsCiL, an adapter-based CiL framework that addresses this limitation of knowledge sharing by incrementally learning shareable skills from different demonstrations, thus enabling sample-efficient task adaptation using the skills particularly in non-stationary CiL environments. In IsCiL, demonstrations are mapped into the state embedding space, where proper skills can be retrieved upon input states through prototype-based memory. These retrievable skills are incrementally learned on their corresponding adapters. Our CiL experiments with complex tasks in Franka-Kitchen and Meta-World demonstrate robust performance of IsCiL in both task adaptation and sample-efficiency. We also show a simple extension of IsCiL for task unlearning scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
