让强化学习主动问人，更好处理有结构和无结构的任务。
Human-Allied Relational Reinforcement Learning
- 用关系强化学习+物体中心表征，统一处理复杂结构与简单数据。
- 通过显式建模策略不确定性，主动向人类专家提问获取指导。
- 在多种任务上比传统方法更快收敛，适合需要人类协作的场景。
过去十年中，强化学习迎来第二次发展浪潮。尽管在图像和视频领域表现卓越，现有系统仍局限于命题式任务，忽略了问题中存在的固有结构。因此，关系强化学习（RRL）被提出以应对结构化问题，并实现对任意数量物体的有效泛化。然而，这类方法对问题结构有强假设。本文提出一种新框架，将RRL与物体中心表征结合，同时处理结构化与非结构化数据。通过显式建模策略不确定性，系统可主动向人类专家查询以获得指导。实验表明，该方法在学习效率与效果上均优于基线。
原文摘要 · Abstract (English)
Reinforcement learning (RL) has experienced a second wind in the past decade. While incredibly successful in images and videos, these systems still operate within the realm of propositional tasks ignoring the inherent structure that exists in the problem. Consequently, relational extensions (RRL) have been developed for such structured problems that allow for effective generalization to arbitrary number of objects. However, they inherently make strong assumptions about the problem structure. We introduce a novel framework that combines RRL with object-centric representation to handle both structured and unstructured data. We enhance learning by allowing the system to actively query the human expert for guidance by explicitly modeling the uncertainty over the policy. Our empirical evaluation demonstrates the effectiveness and efficiency of our proposed approach.
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。