FOE-Dreamer: Deployment-Efficient Learning of Cyber Defense Policies in Operational Networks
FOE-Dreamer is a model-based RL framework for cyber defense that trains online and directly in an emulated operational network on cloud infrastructure, without a simulator stage. It uses a factored world model separating defender-driven, exogenous user activity, and opponent dynamics inferred from defender-observable signals. On an 8-host OpenStack testbed with GHOSTS user emulation and two scripted attacker profiles, it trains in 3 days on a single GPU and reduces episode loss by about 2× vs Rainbow and IQN under matched compute.
