Considerations of Reinforcement Learning within Real-Time Wireless Communication Systems

This paper investigates the practical limitations and considerations of implementing a reinforcement learning framework within real-time wireless communication systems. Trade-offs between latency, memory, goodput, and effects on algorithm accuracy are among the considerations that are analyzed within this work that are not typically considered within simulation-based prior art. To perform this investigation, a representative real-time OFDM transmit/receive chain is implemented within the GNU Radio framework. The system, operating over-the-air through USRPs, leverages reinforcement learning, e.g. Q-Learning, in order to avoid interference with other spectrum users. Performance analysis of this representative system provides a systematic approach for helping to predict limiting factors within an implemented real-time system and thus, aim to provide guidance on how to design these systems with these practical limitations in mind.