LIBERO:面向终身机器人学习的知识迁移基准
LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
AI总结:
LIBERO是一个面向机器人操作的终身学习基准,涵盖130个任务,系统研究陈述性与程序性知识迁移、策略架构、算法、任务顺序鲁棒性及预训练影响,并发现顺序微调优于现有方法。
摘要:
终身学习提供了一种有前景的范式,用于构建能够在整个生命周期内学习和适应的通用智能体。与图像和文本领域中的传统终身学习问题(主要涉及实体和概念的陈述性知识迁移)不同,决策制定中的终身学习(LLDM)还需要迁移程序性知识,例如动作和行为。为了推进LLDM研究,我们引入了LIBERO,一个新颖的机器人操作终身学习基准。具体而言,LIBERO突出了LLDM中的五个关键研究主题:1)如何高效迁移陈述性知识、程序性知识或两者的混合;2)如何设计有效的策略架构和3)有效的LLDM算法;4)终身学习者在任务顺序方面的鲁棒性;以及5)模型预训练对LLDM的影响。我们开发了一个可扩展的程序化生成流水线,原则上可以生成无限多的任务。为了基准测试目的,我们创建了四个任务套件(共130个任务),用于研究上述研究主题。为了支持样本高效学习,我们为所有任务提供了高质量的人类遥操作演示数据。我们的大量实验呈现了几项有见地甚至出乎意料的发现:顺序微调在前向迁移方面优于现有的终身学习方法,没有单一的视觉编码器架构在所有类型的知识迁移中表现出色,以及朴素的监督预训练可能阻碍智能体在后续LLDM中的性能。请访问网站https://libero-project.github.io查看代码和数据集。
英文摘要:
Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the transfer of declarative knowledge of entities and concepts, lifelong learning in decision-making (LLDM) also necessitates the transfer of procedural knowledge, such as actions and behaviors. To advance research in LLDM, we introduce LIBERO, a novel benchmark of lifelong learning for robot manipulation. Specifically, LIBERO highlights five key research topics in LLDM: 1) how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both; 2) how to design effective policy architectures and 3) effective algorithms for LLDM; 4) the robustness of a lifelong learner with respect to task ordering; and 5) the effect of model pretraining for LLDM. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks. For benchmarking purpose, we create four task suites (130 tasks in total) that we use to investigate the above-mentioned research topics. To support sample-efficient learning, we provide high-quality human-teleoperated demonstration data for all tasks. Our extensive experiments present several insightful or even unexpected discoveries: sequential finetuning outperforms existing lifelong learning methods in forward transfer, no single visual encoder architecture excels at all types of knowledge transfer, and naive supervised pretraining can hinder agents' performance in the subsequent LLDM. Check the website at https://libero-project.github.io for the code and the datasets.
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。