Learning to Emulate an Expert Projective Cone Scheduler
This provides a data-driven method for designing scheduling policies based on human expertise, applicable to queueing models in various domains, but it is incremental as it builds on existing multiplicative weights methods.
The paper tackles the problem of automating projective cone scheduling by learning from an expert scheduler, achieving an average loss bound of O(ln(T)√(ln(n)/T)) that converges to zero regardless of system statistics.
Projective cone scheduling defines a large class of rate-stabilizing policies for queueing models relevant to several applications. While there exists considerable theory on the properties of projective cone schedulers, there is little practical guidance on choosing the parameters that define them. In this paper, we propose an algorithm for designing an automated projective cone scheduling system based on observations of an expert projective cone scheduler. We show that the estimated scheduling policy is able to emulate the expert in the sense that the average loss realized by the learned policy will converge to zero. Specifically, for a system with $n$ queues observed over a time horizon $T$, the average loss for the algorithm is $O(\ln(T)\sqrt{\ln(n)/T})$. This upper bound holds regardless of the statistical characteristics of the system. The algorithm uses the multiplicative weights update method and can be applied online so that additional observations of the expert scheduler can be used to improve an existing estimate of the policy. This provides a data-driven method for designing a scheduling policy based on observations of a human expert. We demonstrate the efficacy of the algorithm with a simple numerical example and discuss several extensions.