用逆生成模型从少量示例中快速学会新任务意图
Few-Shot Task Learning through Inverse Generative Modeling
- 通过可逆生成模型，仅用几例演示就能推断新任务概念
- 在5个领域实现未见环境与组合概念的零样本任务生成
- 适合需要快速适应新任务的机器人与智能体应用
从极少示例中学习智能体的意图（如目标或运动风格）极为困难。本文提出少样本任务学习的逆生成建模方法（FTL-IGM），通过预训练可逆神经生成模型，在给定新概念的少量示范后，利用反向传播在不更新模型权重的情况下推断其底层概念。我们在五个领域验证该方法：物体重排、目标导向导航、人体动作描述、自动驾驶和真实桌面操作。实验表明，借助预训练生成模型，该方法能在（1）未见环境中，以及（2）与训练概念组合时，成功学习新概念并生成对应智能体规划或动作。
原文摘要 · Abstract (English)
Learning the intents of an agent, defined by its goals or motion style, is often extremely challenging from just a few examples. We refer to this problem as task concept learning and present our approach, Few-Shot Task Learning through Inverse Generative Modeling (FTL-IGM), which learns new task concepts by leveraging invertible neural generative models. The core idea is to pretrain a generative model on a set of basic concepts and their demonstrations. Then, given a few demonstrations of a new concept (such as a new goal or a new action), our method learns the underlying concepts through backpropagation without updating the model weights, thanks to the invertibility of the generative model. We evaluate our method in five domains -- object rearrangement, goal-oriented navigation, motion caption of human actions, autonomous driving, and real-world table-top manipulation. Our experimental results demonstrate that via the pretrained generative model, we successfully learn novel concepts and generate agent plans or motion corresponding to these concepts in (1) unseen environments and (2) in composition with training concepts.
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。