用温度采样解决机器人数据不平衡问题，提升小任务泛化能力。
Using Temperature Sampling to Effectively Train Robot Learning Policies on Imbalanced Datasets
- 引入温度采样策略，动态调整低频动作的采样概率。
- 在低资源任务上显著提升性能，高资源任务无退化。
- 代码轻量易集成，适合多任务机器人政策训练。
越来越多大型机器人动作与感知数据集被用于训练大型神经网络。这些数据基于具体任务收集，尽管任务描述不同，但常涉及相似的物理动作序列（如‘捡苹果’与‘捡橙子’）。因此，许多机器人数据集在所代表的物理动作上存在显著不平衡。本文提出一种简单的采样策略来缓解这一问题。该方法仅需少量代码即可融入现有框架，能有效提升模型泛化能力。我们在预训练小模型和微调大基础模型两种场景下评估了该方法，在低资源任务上相比先前最先进方法有显著改进，且不损害高资源任务表现。这使得模型容量能更有效地用于多任务策略。我们还在真实世界中对Franka Panda机械臂进行了验证，覆盖多种任务。
原文摘要 · Abstract (English)
Increasingly large datasets of robot actions and sensory observations are being collected to train ever-larger neural networks. These datasets are collected based on tasks and while these tasks may be distinct in their descriptions, many involve very similar physical action sequences (e.g., 'pick up an apple' versus 'pick up an orange'). As a result, many datasets of robotic tasks are substantially imbalanced in terms of the physical robotic actions they represent. In this work, we propose a simple sampling strategy for policy training that mitigates this imbalance. Our method requires only a few lines of code to integrate into existing codebases and improves generalization. We evaluate our method in both pre-training small models and fine-tuning large foundational models. Our results show substantial improvements on low-resource tasks compared to prior state-of-the-art methods, without degrading performance on high-resource tasks. This enables more effective use of model capacity for multi-task policies. We also further validate our approach in a real-world setup on a Franka Panda robot arm across a diverse set of tasks.
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。