Transparent Machine Education of Neural Networks for Swarm Shepherding Using Curriculum Design
This addresses swarm control for robotics or simulation applications, but appears incremental as it applies curriculum design to an existing problem.
The paper tackled the problem of swarm shepherding by designing a curriculum to teach an AI agent to guide agents in complex environments, resulting in enhanced learning speed and behavior complexity.
Swarm control is a difficult problem due to the need to guide a large number of agents simultaneously. We cast the problem as a shepherding problem, similar to biological dogs guiding a group of sheep towards a goal. The shepherd needs to deal with complex and dynamic environments and make decisions in order to direct the swarm from one location to another. In this paper, we design a novel curriculum to teach an artificial intelligence empowered agent to shepherd in the presence of the large state space associated with the shepherding problem and in a transparent manner. The results show that a properly designed curriculum could indeed enhance the speed of learning and the complexity of learnt behaviours.