Can I read Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym): For Rapid Design and Implementation of Distributed Multi-agent Reinforcement Learning Solutions for Wireless Networks on EtoBox?

Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym): For Rapid Design and Implementation of Distributed Multi-agent Reinforcement Learning Solutions for Wireless Networks by Collin Farquhar; Swatantra Kafle; Kian Hamedani; Anu Jagannath; Jithin Jagannath is a Computer Science article available to read on EtoBox.

What is Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym): For Rapid Design and Implementation of Distributed Multi-agent Reinforcement Learning Solutions for Wireless Networks about?

We present the Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym) an open-source architecture designed for accelerating research and development of novel reinforcement learning applied to distributed wireless networks. To ensure an end-to-end architecture, we leverage the existing work of ns3-gym, a software package that allows for using ns-3, a wireless network simulator, as an environment within the OpenAI Gym framework for RL. In addition to this, we have implemented the first known custom CDMA module for ns-3 as well as a framework for RL models with a core suite of implemented algorithms. The software framework capturing the interaction between wireless transceiver (agent) and RL decision engine has been designed to maximize the ease-of-use when testing different RL algorithms and models. In the rest of the paper, we describe these new software components and demonstrate some of the results and capabilities that can be achieved when used in conjunction with the existing open-source ecosystem.

Who reads Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym): For Rapid Design and Implementation of Distributed Multi-agent Reinforcement Learning Solutions for Wireless Networks?

Author

Collin Farquhar; Swatantra Kafle; Kian Hamedani; Anu Jagannath; Jithin Jagannath

Publisher

Elsevier BV

Published

2023

Language

EN

Field

Computer Science (Physical Sciences)