PRISM: PRior-guided Imagination Sampling in world Models 事件

PRISM: PRior-guided Imagination Sampling in world Models arXiv:2606.07974v1 Announce Type: cross Abstract: A learned world model provides a powerful physical intuition for evaluating future states. But its effectiveness in continuous control also depends critically on how candidate actions are generated for model-based planning. Rather than solely asking how accurately a model can simulate the future, we ask: which candidate actions are worth evaluating in the first place? Existing planners typ