Reinforcement learning based on the deep neural network has attracted much attention and has been widely used in real-world applications. However, the black-box property limits its usage from applying in high-stake areas, such as manufacture and healthcare. To deal with this problem, some researchers resort to the interpretable control policy generation algorithm. The basic idea is to use an interpretable model, such as tree-based genetic programming, to extract policy from other black box modes, such as neural networks. Following this idea, in this paper, we try yet another form of the genetic programming technique, evolutionary feature synthesis, to extract control policy from the neural network. We also propose an evolutionary method to optimize the operator set of the control policy for each specific problem automatically. Moreover, a policy simplification strategy is also introduced. We conduct experiments on four reinforcement learning environments. The experiment results reveal that evolutionary feature synthesis can achieve better performance than tree-based genetic programming to extract policy from the neural network with comparable interpretability.

No abstract

No abstract

Background: This study aimed to examine the effects of devazepide on the proliferation, migration, and apoptosis of human bladder cancer (BC) 5637 cells, and its mechanism.Methods: A cell counting kit-8 (CCK-8) for cell viability assays, a colony formation assay, and immunofluorescence were applied to detect the effects of devazepide on the proliferation of 5637 cells. Cell cycle assay, cell apoptosis assay and wound healing assay were performed to detect the effects of devazepide on the cell cycle, apoptosis, and migration of 5637 cells. The protein expression of CyclinD1, Bcl-2associated X protein (Bax), poly ADP-ribose polymerase 1 (PARP1), and Cleaved Caspase-3 in 5637 cells was detected by a western blot assay. Results: The proliferation of 5637 cells was significantly inhibited (P<0.001) after incubation with 12, 25, and 50 μM devazepide for 48 and 72 h. A treatment of 25 μM devazepide for 48 h induced G1-S cell cycle arrest and apoptosis (P<0.01), and inhibited cell migration (P<0.05). By western blot assay, we found that devazepide can down-regulate CyclinD1 expression, and up-regulate Bax, PARP1, and Cleaved Caspase-3 expression. Conclusions: Devazepide inhibits the migration and proliferation of human BC 5637 cells by arresting the G1-S cell cycle, and induces cell apoptosis.

No abstract