用噪声引导的运输方法，仅用20条数据就能高效模仿复杂动作。
Noise-Guided Transport for Imitation Learning
- 将模仿学习建模为对抗训练的最优传输问题，无需预训练
- 在仅20个转移样本下完成高维人形机器人控制任务
- 天然支持不确定性估计，适合数据稀缺场景
我们研究低数据条件下的模仿学习，即仅有少量专家示范可用。在此设置下，依赖大规模预训练或高容量架构的方法难以应用，对示范数据的利用效率至关重要。本文提出轻量级的离线策略方法噪声引导运输（NGT），将模仿学习视为通过对抗训练求解的最优传输问题。NGT无需预训练或特殊架构，天生具备不确定性估计能力，实现简单且易于调参。尽管结构简单，但在挑战性连续控制任务中表现优异，包括高维人形机器人任务，在极端低数据条件下（最少仅20个转移）仍能取得良好效果。
原文摘要 · Abstract (English)
We consider imitation learning in the low-data regime, where only a limited number of expert demonstrations are available. In this setting, methods that rely on large-scale pretraining or high-capacity architectures can be difficult to apply, and efficiency with respect to demonstration data becomes critical. We introduce Noise-Guided Transport (NGT), a lightweight off-policy method that casts imitation as an optimal transport problem solved via adversarial training. NGT requires no pretraining or specialized architectures, incorporates uncertainty estimation by design, and is easy to implement and tune. Despite its simplicity, NGT achieves strong performance on challenging continuous control tasks, including high-dimensional Humanoid tasks, under ultra-low data regimes with as few as 20 transitions.
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。