arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.01463cs.LGcs.AIcs.MA
收藏

基于Actor-Critic优化的目标识别

Goal Recognition using Actor-Critic Optimization

Bar Ilan University(巴伊兰大学);University of Aberdeen(阿伯丁大学);Tufts University(塔夫茨大学)

Ben Nageris, Felipe Meneguzzi, Reuth Mirsky

AI总结:

本文提出DRACO,首个基于深度强化学习从非结构化数据学习策略网络进行目标识别的方法,并引入连续策略表示的新度量,在离散和连续场景中均取得领先性能且成本更低。

摘要:

目标识别旨在从一系列观测中推断智能体的目标。现有方法通常依赖人工设计的领域和离散表示。基于Actor-Critic优化的深度识别(DRACO)是一种基于深度强化学习的新方法,通过两项关键贡献克服了这些局限。第一,它是第一个从非结构化数据中学习一组策略网络并将其用于推断的目标识别算法。第二,DRACO引入了通过连续策略表示评估目标假设的新度量。DRACO在离散场景下实现了目标识别的最先进性能,同时不使用现有方法所用的结构化输入。此外,它在更具挑战性的连续场景中超越了这些方法,并且在计算和内存方面的成本大幅降低。综合来看,这些结果展示了新算法的鲁棒性,连接了传统目标识别与深度强化学习。

英文摘要:

Goal Recognition aims to infer an agent's goal from a sequence of observations. Existing approaches often rely on manually engineered domains and discrete representations. Deep Recognition using Actor-Critic Optimization (DRACO) is a novel approach based on deep reinforcement learning that overcomes these limitations by providing two key contributions. First, it is the first goal recognition algorithm that learns a set of policy networks from unstructured data and uses them for inference. Second, DRACO introduces new metrics for assessing goal hypotheses through continuous policy representations. DRACO achieves state-of-the-art performance for goal recognition in discrete settings while not using the structured inputs used by existing approaches. Moreover, it outperforms these approaches in more challenging, continuous settings at substantially reduced costs in both computing and memory. Together, these results showcase the robustness of the new algorithm, bridging traditional goal recognition and deep reinforcement learning.

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。

↑