让AI实时识别变化中的目标，快速适应新环境。
General Dynamic Goal Recognition using Goal-Conditioned and Meta Reinforcement Learning
- 用无模型目标条件强化学习泛化到新目标
- 在动态噪声环境中实现高精度快速识别
- 适合需要实时目标理解的智能系统
通过行为推断智能体目标是人工智能中的常见问题，称为目标识别（GR）。在目标众多且持续变化的动态环境中，该任务尤为挑战。本文提出广义动态目标识别（GDGR）问题，旨在实现实时自适应的GR系统。论文提出两种新方法：(1) GC-AURA，利用无模型目标条件强化学习实现对新目标的泛化；(2) Meta-AURA，通过元强化学习适应新环境。我们在多种环境中评估了这些方法，证明其在动态和噪声条件下具备快速适应能力和高识别准确率。本工作为在复杂多变的真实世界中实现目标识别迈出了重要一步。
原文摘要 · Abstract (English)
Understanding an agent's goal through its behavior is a common AI problem called Goal Recognition (GR). This task becomes particularly challenging in dynamic environments where goals are numerous and ever-changing. We introduce the General Dynamic Goal Recognition (GDGR) problem, a broader definition of GR aimed at real-time adaptation of GR systems. This paper presents two novel approaches to tackle GDGR: (1) GC-AURA, generalizing to new goals using Model-Free Goal-Conditioned Reinforcement Learning, and (2) Meta-AURA, adapting to novel environments with Meta-Reinforcement Learning. We evaluate these methods across diverse environments, demonstrating their ability to achieve rapid adaptation and high GR accuracy under dynamic and noisy conditions. This work is a significant step forward in enabling GR in dynamic and unpredictable real-world environments.
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。