arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.13965cs.LGstat.ML
收藏

基于图的深度强化学习状态表示

Graph-based State Representation for Deep Reinforcement Learning

L3S Research Center(L3S研究中心);Leibniz University(莱布尼茨大学)

Vikram Waradpande, Daniel Kudenko, Megha Khosla

摘要:

深度强化学习方法的成功很大程度上建立在深度神经网络生成有用的内部表示的能力上。然而,它们具有很高的样本复杂度,并且从良好的输入表示开始可能会对性能产生重大影响。在本文中,我们利用的事实,即潜在的马尔可夫决策过程(MDP)表示一个图,这使我们能够将有效的状态表示学习的拓扑信息。受最近几个图形分析任务的节点表示的成功的启发,我们专门研究了节点表示学习方法在深度RL中有效编码底层MDP拓扑的能力。为此,我们进行了比较分析,从4个不同类别的表示学习算法的策略学习在网格世界的导航任务,这是一个大类的RL问题的代表几个模型。我们发现,所有的嵌入方法优于常用的矩阵表示的网格世界环境中的所有研究的情况下。更重要的是,基于图卷积的方法优于更简单的基于随机游走的方法和图线性自编码器。

英文摘要:

Deep RL approaches build much of their success on the ability of the deep neural network to generate useful internal representations. Nevertheless, they suffer from a high sample-complexity and starting with a good input representation can have a significant impact on the performance. In this paper, we exploit the fact that the underlying Markov decision process (MDP) represents a graph, which enables us to incorporate the topological information for effective state representation learning. Motivated by the recent success of node representations for several graph analytical tasks we specifically investigate the capability of node representation learning methods to effectively encode the topology of the underlying MDP in Deep RL. To this end we perform a comparative analysis of several models chosen from 4 different classes of representation learning algorithms for policy learning in grid-world navigation tasks, which are representative of a large class of RL problems. We find that all embedding methods outperform the commonly used matrix representation of grid-world environments in all of the studied cases. Moreoever, graph convolution based methods are outperformed by simpler random walk based methods and graph linear autoencoders.

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。

↑