Fig. 2

Download original image
Schematic diagram of our framework. The input dimension of the network corresponds to the state dimension in reinforcement learning, which is defined by the combination of the current parameters and the performance metrics of the surrounding four parameters. The output represents the parameter transformation space, with its dimension corresponding to the action space.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.