通过轨迹分割实现指令遵循策略的数据增强
Data Augmentation for Instruction Following Policies via Trajectory Segmentation
AI总结：
本文提出 Play Segmentation（PS）概率模型，通过从无标注轨迹中提取有标签片段来扩充指令-轨迹对数据集，从而显著提升下游指令遵循策略的性能，达到使用两倍标注数据的水平。
摘要：
在机器人或游戏领域，可指令化智能体的可扩展性通常受限于将指令与智能体轨迹配对的有限数据。然而，包含各种智能体行为序列的无标注轨迹（play trajectories）的大型数据集通常是可用的。在半监督设置中，我们探索了从 play trajectories 中提取有标签片段的方法。目标是扩充一个小型的指令-轨迹对标注数据集，以提升通过模仿学习在下游训练的指令遵循策略的性能。假设片段长度变化很小，最近的视频分割方法可以有效地提取有标签片段。为了解决片段长度的约束，我们提出了 Play Segmentation（PS），这是一种概率模型，能够寻找扩展子片段的最大似然分割，同时仅在单个指令片段上进行训练。我们在游戏环境和模拟机器人夹爪设置中的结果强调了分割的重要性；随机采样的片段会降低性能，而结合来自 PS 的有标签片段可将策略性能提升至与使用两倍标注数据训练的策略相同的水平。
英文摘要：
The scalability of instructable agents in robotics or gaming is often hindered by limited data that pairs instructions with agent trajectories. However, large datasets of unannotated trajectories containing sequences of various agent behaviour (play trajectories) are often available. In a semi-supervised setup, we explore methods to extract labelled segments from play trajectories. The goal is to augment a small annotated dataset of instruction-trajectory pairs to improve the performance of an instruction-following policy trained downstream via imitation learning. Assuming little variation in segment length, recent video segmentation methods can effectively extract labelled segments. To address the constraint of segment length, we propose Play Segmentation (PS), a probabilistic model that finds maximum likely segmentations of extended subsegments, while only being trained on individual instruction segments. Our results in a game environment and a simulated robotic gripper setting underscore the importance of segmentation; randomly sampled segments diminish performance, while incorporating labelled segments from PS improves policy performance to the level of a policy trained on twice the amount of labelled data.
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。
