eduzhai > Applied Sciences > Engineering >

Learning Power Control from a Fixed Batch of Data

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: We address how to exploit power control data, gathered from a monitoredenvironment, for performing power control in an unexplored environment. Weadopt offline deep reinforcement learning, whereby the agent learns the policyto produce the transmission powers solely by using the data. Experimentsdemonstrate that despite discrepancies between the monitored and unexploredenvironments, the agent successfully learns the power control very quickly,even if the objective functions in the monitored and unexplored environmentsare dissimilar. About one third of the collected data is sufficient to be ofhigh-quality and the rest can be from any sub-optimal algorithm.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×