DashVMC: Real-Time Discrete World Model Control in Geometry Dash

Excerpt

arXiv:2609.40003v1 Announce Type: new Abstract: World-model agents are usually evaluated in simulators that can wait for the policy; live games impose the opposite constraint, requiring capture, prediction, and action before the next frame. We present DashVMC, which learns a compact, action-conditioned world model from approximately two hours of recorded Geometry Dash gameplay. To test whether the learned dynamics are actionable, a controller is initialized by behavioural cloning (BC) and refine