Author name: Igor Jankowski

arXiv:2604.09523v1 Announce Type: new
Abstract: The transition of Multi-Agent Reinforcement Learning (MARL) policies from simulated cyber wargames to operational Security Operations Centers (SOCs) is fundamentally bottlenecked by the Sim2Real gap. Leg…

arXiv:2603.23722v1 Announce Type: cross
Abstract: While Multi-Agent Reinforcement Learning (MARL) algorithms achieve unprecedented successes across complex continuous domains, their standard deployment strictly adheres to a synchronous operational par…