Reinforcement Learning for Assignment problem

TL;DR

This paper explores using reinforcement learning with neural networks to solve user scheduling problems, demonstrating improved performance over traditional greedy methods in a stochastic simulation environment.

Contribution

It introduces a Q-learning based approach tailored for dynamic user scheduling, outperforming analytical greedy solutions in simulated scenarios.

Findings

Q-learning outperforms greedy algorithms in total reward

The method adapts well to stochastic environment changes

Reinforcement learning reduces scheduling penalties

Abstract

This paper is dedicated to the application of reinforcement learning combined with neural networks to the general formulation of user scheduling problem. Our simulator resembles real world problems by means of stochastic changes in environment. We applied Q-learning based method to the number of dynamic simulations and outperformed analytical greedy-based solution in terms of total reward, the aim of which is to get the lowest possible penalty throughout simulation.