Multi-agent reinforcement learning has recently shown great promise as an approach to networked system control. Arguably, one of the most difficult and important tasks for which large scale networked system control is applicable is common-pool resource management.

For structured pruning, one promising method is to associate each neuron with a scaling factor, and regularize these scaling factors in training.

Wherein, the first step, i.e. gradient estimation, is critical since it provides the essential direction to update variables, which have been explored by many recent works[5,30].