arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.01775cs.ROcs.AIcs.LG
收藏

Eurekaverse:通过大型语言模型生成环境课程

Eurekaverse: Environment Curriculum Generation via Large Language Models

University of Pennsylvania(宾夕法尼亚大学)

William Liang, Sam Wang, Hung-Ju Wang, Osbert Bastani, Dinesh Jayaraman, Yecheng Jason Ma

AI总结:

本文提出Eurekaverse,利用大型语言模型自动生成渐进式环境课程,用于四足机器人跑酷技能训练,并在仿真和现实中验证其优于人工设计的课程。

摘要:

近期研究表明,通过在一系列难度递增的环境课程中训练机器人,是教授机器人各种复杂技能的一种有前景的策略。然而,开发有效的环境分布课程目前需要大量的专业知识,且每个新领域都必须重复这一过程。我们的关键见解是,环境通常自然地表示为代码。因此,我们探究是否可以通过大型语言模型(LLM)的代码生成来实现并自动化有效的环境课程设计。在本文中,我们介绍了Eurekaverse,一种无监督的环境设计算法,它利用LLM来采样越来越具有挑战性、多样性和可学习性的环境,用于技能训练。我们在四足机器人跑酷学习领域验证了Eurekaverse的有效性,在该领域中,四足机器人必须穿越各种障碍课程。Eurekaverse设计的自动课程使得在仿真中逐步学习复杂的跑酷技能成为可能,并且可以成功迁移到现实世界,优于人类设计的手动训练课程。

英文摘要:

Recent work has demonstrated that a promising strategy for teaching robots a wide range of complex skills is by training them on a curriculum of progressively more challenging environments. However, developing an effective curriculum of environment distributions currently requires significant expertise, which must be repeated for every new domain. Our key insight is that environments are often naturally represented as code. Thus, we probe whether effective environment curriculum design can be achieved and automated via code generation by large language models (LLM). In this paper, we introduce Eurekaverse, an unsupervised environment design algorithm that uses LLMs to sample progressively more challenging, diverse, and learnable environments for skill training. We validate Eurekaverse's effectiveness in the domain of quadrupedal parkour learning, in which a quadruped robot must traverse through a variety of obstacle courses. The automatic curriculum designed by Eurekaverse enables gradual learning of complex parkour skills in simulation and can successfully transfer to the real-world, outperforming manual training courses designed by humans.

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。

↑