论文标题

对象类别意识到强化学习

Object-Category Aware Reinforcement Learning

论文作者

Yi, Qi, Zhang, Rui, Peng, Shaohui, Guo, Jiaming, Hu, Xing, Du, Zidong, Zhang, Xishan, Guo, Qi, Chen, Yunji

论文摘要

面向对象的增强学习(OORL)是提高标准RL样本效率和泛化能力的有希望的方法。尝试解决OORL任务的最新作品而没有其他功能工程,主要集中于学习对象表示,然后根据这些对象表示的推理解决任务。但是,这些作品都没有试图明确模拟同一类别的不同对象实例之间的固有相似性。同一类别的对象应具有相似的功能;因此,类别是对象的最关键属性。遵循此见解,我们提出了一个名为“对象类别”的新型框架(OCARL),该框架利用对象的类别信息来促进感知和推理。 OCARL由三个部分组成:(1)类别意识到无监督的对象发现(UOD),它发现对象及其相应的类别; (2)对象类别意识到的感知,该感知编码类别信息,并且同时对(1)的不完整性也很强; (3)以对象为中心的模块化推理,该推理基于对象时会采用多个独立和对象类别的网络。我们的实验表明,Ocarl可以提高OORL结构域的样本效率和概括。

Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL. Recent works that try to solve OORL tasks without additional feature engineering mainly focus on learning the object representations and then solving tasks via reasoning based on these object representations. However, none of these works tries to explicitly model the inherent similarity between different object instances of the same category. Objects of the same category should share similar functionalities; therefore, the category is the most critical property of an object. Following this insight, we propose a novel framework named Object-Category Aware Reinforcement Learning (OCARL), which utilizes the category information of objects to facilitate both perception and reasoning. OCARL consists of three parts: (1) Category-Aware Unsupervised Object Discovery (UOD), which discovers the objects as well as their corresponding categories; (2) Object-Category Aware Perception, which encodes the category information and is also robust to the incompleteness of (1) at the same time; (3) Object-Centric Modular Reasoning, which adopts multiple independent and object-category-specific networks when reasoning based on objects. Our experiments show that OCARL can improve both the sample efficiency and generalization in the OORL domain.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源