
Optimal Network Control in PartiallyControllable Networks
The effectiveness of many optimal network control algorithms (e.g., Back...
read it

Few Shot System Identification for Reinforcement Learning
Learning by interaction is the key to skill acquisition for most living ...
read it

COVID19 Pandemic Cyclic Lockdown Optimization Using Reinforcement Learning
This work examines the use of reinforcement learning (RL) to optimize cy...
read it

Reinforcement Learning based Interconnection Routing for Adaptive Traffic Optimization
Applying Machine Learning (ML) techniques to design and optimize compute...
read it

ModelicaGym: Applying Reinforcement Learning to Modelica Models
This paper presents ModelicaGym toolbox that was developed to employ Rei...
read it

QFlow: A Reinforcement Learning Approach to High QoE Video Streaming over Wireless Networks
Wireless Internet access has brought legions of heterogeneous applicatio...
read it

Stable Reinforcement Learning with Unbounded State Space
We consider the problem of reinforcement learning (RL) with unbounded st...
read it
RLQN: A Reinforcement Learning Framework for Optimal Control of Queueing Systems
With the rapid advance of information technology, network systems have become increasingly complex and hence the underlying system dynamics are often unknown or difficult to characterize. Finding a good network control policy is of significant importance to achieve desirable network performance (e.g., high throughput or low delay). In this work, we consider using modelbased reinforcement learning (RL) to learn the optimal control policy for queueing networks so that the average job delay (or equivalently the average queue backlog) is minimized. Traditional approaches in RL, however, cannot handle the unbounded state spaces of the network control problem. To overcome this difficulty, we propose a new algorithm, called Reinforcement Learning for Queueing Networks (RLQN), which applies modelbased RL methods over a finite subset of the state space, while applying a known stabilizing policy for the rest of the states. We establish that the average queue backlog under RLQN with an appropriately constructed subset can be arbitrarily close to the optimal result. We evaluate RLQN in dynamic server allocation, routing and switching problems. Simulation results show that RLQN minimizes the average queue backlog effectively.
READ FULL TEXT
Comments
There are no comments yet.