Learning Power Control from a Fixed Batch of Data

TL;DR

This paper presents an offline deep reinforcement learning approach to adapt power control policies from monitored environment data to new, unexplored environments, demonstrating rapid learning despite environmental differences.

Contribution

It introduces a method for effective power control policy transfer using offline RL with limited and sub-optimal data, addressing environmental discrepancies.

Findings

Agent learns power control quickly in new environments.

High-quality policies achieved with only one-third of collected data.

Sub-optimal data from other algorithms can be effectively used.

Abstract

We address how to exploit power control data, gathered from a monitored environment, for performing power control in an unexplored environment. We adopt offline deep reinforcement learning, whereby the agent learns the policy to produce the transmission powers solely by using the data. Experiments demonstrate that despite discrepancies between the monitored and unexplored environments, the agent successfully learns the power control very quickly, even if the objective functions in the monitored and unexplored environments are dissimilar. About one third of the collected data is sufficient to be of high-quality and the rest can be from any sub-optimal algorithm.