Poster: Learning to shine – optimizing glossy at runtime with reinforcement learning

Poirot, ValentinValentinPoirotLandsiedel, OlafOlafLandsiedel2025-02-062025-02-062019-02International Conference on Embedded Wireless Systems and Networks, EWSN 2019: 226-227978-0-9949-8863-8https://hdl.handle.net/11420/53891Glossy is a dissemination protocol that allows a node to propagate information to the entire network through constructive interference. We present GLOSSAI, a new artificial intelligence-based version of Glossy. We use reinforcement learning to determine and update Glossy’s parameters at runtime. Each node individually learns the best strategy to minimize energy consumption while maintaining high reliability. Furthermore, nodes can dynamically adapt their parameters to follow the dynamics of the medium.enMLE@TUHHTechnology::600: TechnologyPoster: Learning to shine – optimizing glossy at runtime with reinforcement learningConference PaperConference Paper