We propose a federated reinforcement learning (FedRL) solution to innovate resource allocation in converged access networks. FedRL lowers network latency with reinforcement-learnt bandwidth decision and achieves fast learning with federated learning efforts.
© 2020 The Author(s)
You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
Login to access OSA Member Subscription