让机器人训练任务更贴近真实世界，提升学习效率与导航成功率。
Grounded Curriculum Learning
- 根据真实任务分布动态调整仿真训练任务，避免偏差。
- 在复杂导航任务上成功率达6.8%和6.5%的提升。
- 适合需要高效现实迁移的机器人强化学习研究者。
机器人强化学习（RL）因真实数据成本高昂，广泛依赖模拟器。尽管已有大量工作致力于提升模拟器动力学模型的真实性，但模拟环境与真实世界之间还存在另一关键差异：可用训练任务的分布不一致。现有课程学习方法自动调整仿真任务分布，却未考虑其与真实世界的关联性，进一步加剧了这一差距。为此，本文提出基于真实任务分布的课程学习（GCL），在自适应课程中对齐仿真任务分布，并显式考虑机器人过往被分配的任务及其表现。我们在BARN数据集上的复杂导航任务中验证了GCL，相较于最先进的课程学习方法和人工设计的课程，分别实现了6.8%和6.5%的成功率提升。结果表明，将仿真任务分布锚定于真实世界，可显著提升学习效率与导航性能。
原文摘要 · Abstract (English)
The high cost of real-world data for robotics Reinforcement Learning (RL) leads to the wide usage of simulators. Despite extensive work on building better dynamics models for simulators to match with the real world, there is another, often-overlooked mismatch between simulations and the real world, namely the distribution of available training tasks. Such a mismatch is further exacerbated by existing curriculum learning techniques, which automatically vary the simulation task distribution without considering its relevance to the real world. Considering these challenges, we posit that curriculum learning for robotics RL needs to be grounded in real-world task distributions. To this end, we propose Grounded Curriculum Learning (GCL), which aligns the simulated task distribution in the curriculum with the real world, as well as explicitly considers what tasks have been given to the robot and how the robot has performed in the past. We validate GCL using the BARN dataset on complex navigation tasks, achieving a 6.8% and 6.5% higher success rate compared to a state-of-the-art CL method and a curriculum designed by human experts, respectively. These results show that GCL can enhance learning efficiency and navigation performance by grounding the simulation task distribution in the real world within an adaptive curriculum.
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。