כתבה
arXiv cs.LG ·
DashVMC: ניהול עולם דיסקרטי בזמן אמת ב-Geometry Dash
DashVMC: Real-Time Discrete World Model Control in Geometry Dash
DashVMC היא טכנולוגיה של ניהול עולם דיסקרטי בזמן אמת, שנלמדה משחקי Geometry Dash. היא מאפשרת ניהול עולם דיסקרטי בזמן אמת, והיא נלמדה על ידי Proximal Policy Optimization (PPO).
תקציר מקורי באנגליתarXiv: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 refined with Proximal Policy Optimization (PPO) entirely in frozen-model rollouts, without further interaction with the live game. Across three controller seeds, the refined policies survive longer than their BC initializations on all three official levels and a held-out community layout. At deployment, t
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית