be obtained from G by an application of a set of edge weight updates to G. Let s\in V and let T_{s} and T_{s}^{\prime} be Shortest Path Trees (SPTs) rooted at s in G and G^{\prime}, respectively. The ...

To address this problem, we propose a Query ... graph (KG) and develops a reinforcement learning approach, characterized by the demonstration-guided policy network and query-aware rewards, to perform ...