Graph Policy Gradients for Large Scale Robot Control
This addresses scalability in multi-robot control, offering a solution for large-scale applications like formation flying, though it is incremental as it builds on existing graph and reinforcement learning methods.
The paper tackles the problem of learning control policies for many homogeneous robots by proposing Graph Policy Gradients (GPG), which uses graph convolutional networks to exploit symmetry and reduce dimensionality, enabling zero-shot transfer from policies trained on three robots to over a hundred robots.
In this paper, we consider the problem of learning policies to control a large number of homogeneous robots. To this end, we propose a new algorithm we call Graph Policy Gradients (GPG) that exploits the underlying graph symmetry among the robots. The curse of dimensionality one encounters when working with a large number of robots is mitigated by employing a graph convolutional neural (GCN) network to parametrize policies for the robots. The GCN reduces the dimensionality of the problem by learning filters that aggregate information among robots locally, similar to how a convolutional neural network is able to learn local features in an image. Through experiments on formation flying, we show that our proposed method is able to scale better than existing reinforcement methods that employ fully connected networks. More importantly, we show that by using our locally learned filters we are able to zero-shot transfer policies trained on just three robots to over hundred robots.