arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.06356cs.AIcs.LG
收藏

作为强化学习的目标识别

Goal Recognition as Reinforcement Learning

Pontifícia Universidade Católica do Rio Grande do Sul(南里奥格兰德天主教大学);University of Aberdeen(阿伯丁大学);Bar Ilan University(巴伊兰大学);The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Leonardo Rosa Amado, Reuth Mirsky, Felipe Meneguzzi

AI总结:

针对现有目标识别方法依赖人工领域设计、实时计算成本高且抗噪性弱的问题,提出结合无模型强化学习的两阶段目标识别框架,其表格Q-learning实例在标准基准上达SOTA,噪声环境下性能更优。

摘要:

大多数目标识别方法都依赖于对行动者在环境中追求目标时可能的动态特性的规范描述。这类规范存在两个关键问题:其一,对这些动态特性进行编码需要领域专家的精心设计,且在识别阶段通常对噪声的鲁棒性不足;其二,现有方法往往需要高成本的实时计算来推断每个潜在目标的可能性。本文提出了一种结合无模型强化学习与目标识别的框架,以减少对精细人工领域设计的需求,同时降低高成本在线执行的开销。该框架包含两个主要阶段:针对每个潜在目标离线学习策略或效用函数,以及在线推理阶段。我们给出了该框架的首个实现实例,在学习阶段采用表格型Q-learning,并提出三种可用于推理阶段的度量指标。该实例在标准评估领域上的性能达到了现有目标识别器的最优水平,且在噪声环境下表现更优。

英文摘要:

Most approaches for goal recognition rely on specifications of the possible dynamics of the actor in the environment when pursuing a goal. These specifications suffer from two key issues. First, encoding these dynamics requires careful design by a domain expert, which is often not robust to noise at recognition time. Second, existing approaches often need costly real-time computations to reason about the likelihood of each potential goal. In this paper, we develop a framework that combines model-free reinforcement learning and goal recognition to alleviate the need for careful, manual domain design, and the need for costly online executions. This framework consists of two main stages: Offline learning of policies or utility functions for each potential goal, and online inference. We provide a first instance of this framework using tabular Q-learning for the learning stage, as well as three measures that can be used to perform the inference stage. The resulting instantiation achieves state-of-the-art performance against goal recognizers on standard evaluation domains and superior performance in noisy environments.

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。

↑