arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1708.07280cs.AI
收藏

使用深度神经网络学习广义反应策略

Learning Generalized Reactive Policies using Deep Neural Networks

University of California, Berkeley(加州大学伯克利分校);Princeton University(普林斯顿大学);Arizona State University(亚利桑那州立大学)

Edward Groshev, Maxwell Goldstein, Aviv Tamar, Siddharth Srivastava, Pieter Abbeel

摘要:

我们提出了一种新的方法来学习规划,在解决一组给定的规划问题,而获得的知识被用来规划相关的,但新的问题实例更快。我们表明,深度神经网络可用于学习和表示将问题实例和状态映射到动作的\emph{generalized reactive policy}(GRP),并且学习的GRP有效地解决了大量具有挑战性的问题实例。在这个方向上的先前的努力相比,我们的方法显着减少了手工制作的领域知识或特征选择的学习的依赖。相反,GRP使用一组成功的执行跟踪从头开始训练。我们表明,我们的方法也可以用来自动学习的启发式函数,可用于定向搜索算法。我们评估我们的方法使用一套广泛的实验两个具有挑战性的规划问题域,并表明我们的方法有利于学习复杂的决策政策和强大的启发式功能,以最少的人力投入。我们的结果视频可在goo.gl/Hpy4e3上获得。

英文摘要:

We present a new approach to learning for planning, where knowledge acquired while solving a given set of planning problems is used to plan faster in related, but new problem instances. We show that a deep neural network can be used to learn and represent a \emph{generalized reactive policy} (GRP) that maps a problem instance and a state to an action, and that the learned GRPs efficiently solve large classes of challenging problem instances. In contrast to prior efforts in this direction, our approach significantly reduces the dependence of learning on handcrafted domain knowledge or feature selection. Instead, the GRP is trained from scratch using a set of successful execution traces. We show that our approach can also be used to automatically learn a heuristic function that can be used in directed search algorithms. We evaluate our approach using an extensive suite of experiments on two challenging planning problem domains and show that our approach facilitates learning complex decision making policies and powerful heuristic functions with minimal human input. Videos of our results are available at goo.gl/Hpy4e3.

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。

↑