arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.12335cs.AI
收藏

通过深度Q学习选择子目标进行目标推理

Goal Reasoning by Selecting Subgoals with Deep Q-Learning

Universidad de Granada(格拉纳达大学)

Carlos Núñez-Molina, Vladislav Nikolov, Ignacio Vellido, Juan Fernández-Olivares

摘要:

在这项工作中,我们提出了一种目标推理方法,该方法通过深度Q学习来选择子目标,以便在面临时间限制很紧的场景(例如在线执行系统)时减少计划器的负载。我们设计了一个基于CNN的目标选择模块,并在标准的视频游戏环境中对其进行了训练,在不同的游戏(规划域)和级别(规划问题)上对其进行了测试,以衡量其泛化能力。当比较它的性能与一个令人满意的规划器,得到的结果表明,这两种方法都能够找到高质量的计划,但我们的方法大大减少了规划时间。我们得出结论,我们的方法可以成功地应用到不同类型的域(游戏),并显示出良好的泛化性能时,在同一个游戏(域)的新的水平(问题)进行评估。

英文摘要:

In this work we propose a goal reasoning method which learns to select subgoals with Deep Q-Learning in order to decrease the load of a planner when faced with scenarios with tight time restrictions, such as online execution systems. We have designed a CNN-based goal selection module and trained it on a standard video game environment, testing it on different games (planning domains) and levels (planning problems) to measure its generalization abilities. When comparing its performance with a satisfying planner, the results obtained show both approaches are able to find plans of good quality, but our method greatly decreases planning time. We conclude our approach can be successfully applied to different types of domains (games), and shows good generalization properties when evaluated on new levels (problems) of the same game (domain).

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。

↑