FOE-Dreamer: Deployment-Efficient Learning of Cyber Defense Policies in Operational Networks

arXiv:2611.14880v1 Announce Type: new Abstract: Autonomous cyber defense is widely studied with deep reinforcement learning, but most work trains policies inside simulators because learning requires many trial-and-error interactions. Simulator-based training carries a fidelity gap: trained policies face authentication delays, partial action failures, service dependencies, and user traffic patterns that the simulator did not represent, and degrade on transfer. Training directly in the network being defended removes the gap but makes every interaction slow and costly, so sample efficiency becomes the binding constraint.