论文标题
MODRL/D-AM：使用分解和注意模型进行多目标优化的多物镜深钢筋学习算法
MODRL/D-AM: Multiobjective Deep Reinforcement Learning Algorithm Using Decomposition and Attention Model for Multiobjective Optimization
论文作者
论文摘要
最近，提出了一种深入的增强学习方法来解决多目标优化问题。在这种方法中，多目标优化问题分解为许多单目标优化子问题，所有子问题都以协作方式优化。每个子问题都用指针网络建模，并通过强化学习对模型进行训练。但是，当指针网络提取实例的功能时，它会忽略输入节点的基础结构信息。因此，本文提出了一种使用分解和注意模型来解决多目标优化问题的多目标深钢筋学习方法。在我们的方法中，每个子问题都通过注意力模型解决，该模型可以利用结构特征以及输入节点的节点特征。多物理旅行推销员问题的实验结果表明，与以前的方法相比，提出的算法取得了更好的性能。
Recently, a deep reinforcement learning method is proposed to solve multiobjective optimization problem. In this method, the multiobjective optimization problem is decomposed to a number of single-objective optimization subproblems and all the subproblems are optimized in a collaborative manner. Each subproblem is modeled with a pointer network and the model is trained with reinforcement learning. However, when pointer network extracts the features of an instance, it ignores the underlying structure information of the input nodes. Thus, this paper proposes a multiobjective deep reinforcement learning method using decomposition and attention model to solve multiobjective optimization problem. In our method, each subproblem is solved by an attention model, which can exploit the structure features as well as node features of input nodes. The experiment results on multiobjective travelling salesman problem show the proposed algorithm achieves better performance compared with the previous method.
