让机器人自动设计训练课程，提升复杂任务成功率
GACL: Grounded Adaptive Curriculum Learning with Active Task and Performance Monitoring
- 基于任务表征与性能监控，动态生成适应机器人的训练课程
- 在受限环境导航和3D空间行走任务中，成功率分别提升6.8%和6.1%
- 适合研究机器人自主训练、强化学习策略优化的开发者
课程学习为训练复杂机器人任务提供了有前景的方案，但现有方法多依赖人工设计课程，耗时且易受主观偏差影响。尽管自动化课程学习在网格世界和游戏等简单领域表现良好，但在机器人任务中面临挑战：需处理复杂任务空间，同时保持与目标域分布的相关性，而后者仅能通过有限样本部分知晓。为此，我们提出基于接地的自适应课程学习（GACL）框架，包含三大创新：(1) 一致处理复杂机器人任务设计的任务表征；(2) 主动性能跟踪机制，实现根据机器人当前能力自适应生成课程；(3) 接地方法，通过在参考任务与合成任务间交替采样，维持目标域相关性。我们在轮式机器人受限环境导航和四足机器人在复杂3D封闭空间行走任务上验证了GACL，分别取得比最先进方法高出6.8%和6.1%的成功率。
原文摘要 · Abstract (English)
Curriculum learning has emerged as a promising approach for training complex robotics tasks, yet current applications predominantly rely on manually designed curricula, which demand significant engineering effort and can suffer from subjective and suboptimal human design choices. While automated curriculum learning has shown success in simple domains like grid worlds and games where task distributions can be easily specified, robotics tasks present unique challenges: they require handling complex task spaces while maintaining relevance to target domain distributions that are only partially known through limited samples. To this end, we propose Grounded Adaptive Curriculum Learning, a framework specifically designed for robotics curriculum learning with three key innovations: (1) a task representation that consistently handles complex robot task design, (2) an active performance tracking mechanism that allows adaptive curriculum generation appropriate for the robot's current capabilities, and (3) a grounding approach that maintains target domain relevance through alternating sampling between reference and synthetic tasks. We validate GACL on wheeled navigation in constrained environments and quadruped locomotion in challenging 3D confined spaces, achieving 6.8% and 6.1% higher success rates, respectively, than state-of-the-art methods in each domain.
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。