Fig. 9From: Selective network discovery via deep reinforcement learning on embedded spacesEntropy versus time step for all tested embeddings and configurations. Here we see that MOD, PPR, LAPLACE, and GLEE are able to compress the action space, which is indicated by the sharp drops in entropy before the entire anomaly has been discovered (\({<}\)Â 40 steps). This is especially pronounced in the easier cases, e.g. denser anomalies, illustrated in the leftmost plots for each embedding. Sharp increases in entropy values correspond to the agent moving from one anomalous subnetwork to the other and it is faced with intermediate boundary sets with no target nodesBack to article page