arXiv Machine Learning By Jiaqi Li, Xinglong Zhang, Haibin Xie, Yixing Lan, Wei Pan, Xin Xu

Koopman Dreamer: Spectrally Constrained Latent Dynamics for Stable World-Model Imagination

Read the original on arXiv Machine Learning →

arXiv:2607. 19719v1 Announce Type: new Abstract: Latent world models improve sample efficiency in continuous control by optimizing policies over imagined latent trajectories, but common neural transitions offer limited direct control over modal persistence and error accumulation in long rollouts.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.