arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.06876cs.AIcs.RO
收藏

面向规划的动作成本预测的决策聚焦学习

Decision-Focused Learning to Predict Action Costs for Planning

KU Leuven(鲁汶大学);Saarland University(萨尔大学);LAAS-CNRS(法国国家科学研究中心自动控制与系统分析实验室);Australian National University(澳大利亚国立大学);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心)

Jayanta Mandi, Marco Foschini, Daniel Holler, Sylvie Thiebaux, Jorg Hoffmann, Tias Guns

AI总结:

本文首次将决策聚焦学习应用于自动规划中的动作成本预测,提出新的梯度计算方法解决负动作成本问题,并引入缓存机制提升可扩展性,实验证明其生成的计划显著优于最小化预测误差的方法。

摘要:

在许多自动规划应用中,动作成本可能难以指定。一个例子是通过某一路段所需的时间,这取决于许多因素,例如当前的天气条件。解决这一问题的一种自然方法是基于输入特征(例如天气预报)学习预测这些参数,随后在自动规划中使用预测的动作成本。Decision-Focused Learning (DFL) 在学习预测组合优化问题的参数方面取得了成功,其方式是优化解的质量而非预测质量。这种方法比将预测和优化作为独立任务处理能产生更好的结果。在本文中,我们首次研究了实现 DFL 用于自动规划以学习预测动作成本的挑战。需要克服两个主要挑战:(1) 在梯度下降学习过程中会调用规划系统,以解决规划中不支持的负动作成本问题。我们提出了新的梯度计算方法来避免这一问题。(2) DFL 在训练期间需要重复调用规划器,这可能限制该方法的可扩展性。我们实验了近似最优计划的不同方法,以及一种易于实现的缓存机制来加速学习过程。作为首个解决自动规划 DFL 的工作,我们证明所提出的梯度计算持续产生比旨在最小化预测误差的预测显著更好的计划;并且缓存能够缓解计算需求。

英文摘要:

In many automated planning applications, action costs can be hard to specify. An example is the time needed to travel through a certain road segment, which depends on many factors, such as the current weather conditions. A natural way to address this issue is to learn to predict these parameters based on input features (e.g., weather forecasts) and use the predicted action costs in automated planning afterward. Decision-Focused Learning (DFL) has been successful in learning to predict the parameters of combinatorial optimization problems in a way that optimizes solution quality rather than prediction quality. This approach yields better results than treating prediction and optimization as separate tasks. In this paper, we investigate for the first time the challenges of implementing DFL for automated planning in order to learn to predict the action costs. There are two main challenges to overcome: (1) planning systems are called during gradient descent learning, to solve planning problems with negative action costs, which are not supported in planning. We propose novel methods for gradient computation to avoid this issue. (2) DFL requires repeated planner calls during training, which can limit the scalability of the method. We experiment with different methods approximating the optimal plan as well as an easy-to-implement caching mechanism to speed up the learning process. As the first work that addresses DFL for automated planning, we demonstrate that the proposed gradient computation consistently yields significantly better plans than predictions aimed at minimizing prediction error; and that caching can temper the computation requirements.

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。

↑