Reinforcement learning algorithms for adaptive load balancing in publish/subscribe systems: PPO, UCB, and epsilon-greedy approaches

URN:NBN:SI:DOC-YZ5A8OFI2025Al Shaikh, Rana ZuhairAl-Nayar, Muna M. JawadHasan, Ahmed M.documents/doc/Y/URN_NBN_SI_doc-YZ5A8OFI_001.pdfdocuments/doc/Y/URN_NBN_SI_doc-YZ5A8OFI_001.txt497articlestr. 77-8810.31449/inf.v49i7.68951854-3871236308483URN:NBN:SI:doc-YZ5A8OFIengInformatikaInformatica (Ljubljana)BYobjavaporazdelitev obremenitveprijavapub/sup systemučenje z okrepitvijoumetna inteligencaReinforcement learning algorithms for adaptive load balancing in publish/subscribe systems: PPO, UCB, and epsilon-greedy approaches