Reproduce “Joint Channel Selection using FedDRL in V2X” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Lorenzo Mancini, Safwan Labbi, Karim Abed Meraim, Fouzi Boukhalfa, Alain Durmus, Paul Mangold, Eric Moulines
FedPPO trains a shared channel-selection policy for simulated vehicles choosing between DSRC radio and visible-light links. Vehicles learn locally from road settings, then a server averages model parameters without collecting raw trajectories. The all-setting policy achieves mean Packet Delivery Ratio (PDR) of 0.874, versus 0.804 for the strongest single-setting baseline, but ties it on highway and does not meet QoS requirements.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.